# SLM Lab

## v4.2.0

- [SLM Lab](https://slm-lab.gitbook.io/slm-lab/v4.2.0/master.md): Modular Deep Reinforcement Learning framework in PyTorch.
- [Installation](https://slm-lab.gitbook.io/slm-lab/v4.2.0/setup/installation.md)
- [Quick Start](https://slm-lab.gitbook.io/slm-lab/v4.2.0/setup/quick-start.md): To test the installation.
- [Lab Command](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/slm-lab-command.md)
- [Lab Organization](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/lab-organization.md)
- [Train: REINFORCE CartPole](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/train-and-enjoy-dqn-cartpole.md)
- [Resume and Enjoy: REINFORCE CartPole](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/resume-and-enjoy-reinforce-cartpole.md)
- [Agent Spec: DDQN+PER on LunarLander](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/agent-spec-ddqn+per-on-lunarlander.md)
- [Env Spec: A2C on Pong](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/environment-spec-a2c-on-bipedalwalker.md)
- [GPU Usage: PPO on Pong](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/gpu-usage-ppo-on-pong.md)
- [Parallelizing Training: Async SAC on Humanoid](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/parallelizing-training-async-sac-on-humanoid.md)
- [Experiment and Search Spec: PPO on Breakout](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/search-spec-ppo-on-breakout.md)
- [Run Benchmark: A2C on Atari Games](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/run-benchmark-a2c-on-atari-games.md)
- [Meta Spec: High Level Specifications](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/meta-spec-high-level-specifications.md)
- [Post-Hoc Analysis](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/post-hoc-analysis.md)
- [TensorBoard: Visualizing Models and Actions](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/tensorboard-visualizing-models-and-actions.md)
- [Using SLM Lab In Your Project](https://slm-lab.gitbook.io/slm-lab/v4.2.0/using-slm-lab/using-slm-lab-in-your-project.md)
- [Data Locations](https://slm-lab.gitbook.io/slm-lab/v4.2.0/analyzing-results/analytics.md)
- [Graphs and Data](https://slm-lab.gitbook.io/slm-lab/v4.2.0/analyzing-results/session-graph.md)
- [Performance Metrics](https://slm-lab.gitbook.io/slm-lab/v4.2.0/analyzing-results/performance-metrics.md)
- [Public Benchmark Data](https://slm-lab.gitbook.io/slm-lab/v4.2.0/benchmark-results/public-benchmark-data.md)
- [Discrete Environment Benchmark](https://slm-lab.gitbook.io/slm-lab/v4.2.0/benchmark-results/discrete-benchmark.md)
- [Continuous Environment Benchmark](https://slm-lab.gitbook.io/slm-lab/v4.2.0/benchmark-results/continuous-benchmark.md)
- [Atari Environment Benchmark](https://slm-lab.gitbook.io/slm-lab/v4.2.0/benchmark-results/atari-benchmark.md)
- [RL GIFs](https://slm-lab.gitbook.io/slm-lab/v4.2.0/benchmark-results/rl-gifs.md): A collection of replay GIFs generated from SLM Lab agents in "enjoy" mode.
- [Modular Design](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/modular-lab-components.md)
- [Algorithm Taxonomy](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/modular-lab-components/algorithm-taxonomy.md)
- [Class Inheritance: A2C > PPO](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/modular-lab-components/class-inheritance-a2c-greater-than-ppo.md)
- [Algorithm](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/algorithms.md)
- [DQN](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/algorithms/dqn.md)
- [REINFORCE](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/algorithms/reinforce.md)
- [Actor Critic](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/algorithms/a2c.md)
- [Memory](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/memory.md)
- [Replay](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/memory/replay.md)
- [PrioritizedReplay](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/memory/prioritizedreplay.md)
- [OnPolicyReplay](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/memory/batch.md)
- [OnPolicyBatchReplay](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/memory/episodic.md)
- [Net](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/neural-networks.md)
- [MLP](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/neural-networks/mlp.md)
- [CNN](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/neural-networks/cnn.md)
- [RNN](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/neural-networks/rnn.md)
- [Profiling SLM Lab](https://slm-lab.gitbook.io/slm-lab/v4.2.0/development/profiling-slm-lab.md)
- [Book: Foundations of Deep Reinforcement Learning](https://slm-lab.gitbook.io/slm-lab/v4.2.0/publications-and-talks/instruction-for-the-book-+-intro-to-rl-section.md)
- [Talks and Presentations](https://slm-lab.gitbook.io/slm-lab/v4.2.0/publications-and-talks/talks-given-with-slm-lab.md)
- [Deep RL Resources](https://slm-lab.gitbook.io/slm-lab/v4.2.0/resources/untitled.md)
- [Contributing](https://slm-lab.gitbook.io/slm-lab/v4.2.0/resources/contributing.md)
- [Motivation](https://slm-lab.gitbook.io/slm-lab/v4.2.0/resources/motivation.md)
- [Help](https://slm-lab.gitbook.io/slm-lab/v4.2.0/resources/help.md)
- [Contact](https://slm-lab.gitbook.io/slm-lab/v4.2.0/resources/contacts.md)

## v4.1.1

- [SLM Lab](https://slm-lab.gitbook.io/slm-lab/master/master.md): Modular Deep Reinforcement Learning framework in PyTorch.
- [Installation](https://slm-lab.gitbook.io/slm-lab/master/setup/installation.md)
- [Quick Start](https://slm-lab.gitbook.io/slm-lab/master/setup/quick-start.md): To test the installation.
- [Lab Command](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/slm-lab-command.md)
- [Lab Organization](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/lab-organization.md)
- [Train and Enjoy: REINFORCE CartPole](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/train-and-enjoy-dqn-cartpole.md)
- [Agent Spec: DDQN+PER on LunarLander](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/agent-spec-ddqn+per-on-lunarlander.md)
- [Env Spec: A2C on Pong](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/environment-spec-a2c-on-bipedalwalker.md)
- [GPU Usage: PPO on Pong](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/gpu-usage-ppo-on-pong.md)
- [Parallelizing Training: Async SAC on Humanoid](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/parallelizing-training-async-sac-on-humanoid.md)
- [Experiment and Search Spec: PPO on Breakout](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/search-spec-ppo-on-breakout.md)
- [Run Benchmark: A2C on Atari Games](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/run-benchmark-a2c-on-atari-games.md)
- [Meta Spec: High Level Specifications](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/meta-spec-high-level-specifications.md)
- [Post-Hoc Analysis](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/post-hoc-analysis.md)
- [TensorBoard: Visualizing Models and Actions](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/tensorboard-visualizing-models-and-actions.md)
- [Using SLM Lab In Your Project](https://slm-lab.gitbook.io/slm-lab/master/using-slm-lab/using-slm-lab-in-your-project.md)
- [Data Locations](https://slm-lab.gitbook.io/slm-lab/master/analyzing-results/analytics.md)
- [Graphs and Data](https://slm-lab.gitbook.io/slm-lab/master/analyzing-results/session-graph.md)
- [Performance Metrics](https://slm-lab.gitbook.io/slm-lab/master/analyzing-results/performance-metrics.md)
- [Public Benchmark Data](https://slm-lab.gitbook.io/slm-lab/master/benchmark-results/public-benchmark-data.md)
- [Discrete Environment Benchmark](https://slm-lab.gitbook.io/slm-lab/master/benchmark-results/discrete-benchmark.md)
- [Continuous Environment Benchmark](https://slm-lab.gitbook.io/slm-lab/master/benchmark-results/continuous-benchmark.md)
- [Atari Environment Benchmark](https://slm-lab.gitbook.io/slm-lab/master/benchmark-results/atari-benchmark.md)
- [RL GIFs](https://slm-lab.gitbook.io/slm-lab/master/benchmark-results/rl-gifs.md): A collection of replay GIFs generated from SLM Lab agents in "enjoy" mode.
- [Modular Design](https://slm-lab.gitbook.io/slm-lab/master/development/modular-lab-components.md)
- [Algorithm Taxonomy](https://slm-lab.gitbook.io/slm-lab/master/development/modular-lab-components/algorithm-taxonomy.md)
- [Class Inheritance: A2C > PPO](https://slm-lab.gitbook.io/slm-lab/master/development/modular-lab-components/class-inheritance-a2c-greater-than-ppo.md)
- [Algorithm](https://slm-lab.gitbook.io/slm-lab/master/development/algorithms.md)
- [DQN](https://slm-lab.gitbook.io/slm-lab/master/development/algorithms/dqn.md)
- [REINFORCE](https://slm-lab.gitbook.io/slm-lab/master/development/algorithms/reinforce.md)
- [Actor Critic](https://slm-lab.gitbook.io/slm-lab/master/development/algorithms/a2c.md)
- [Memory](https://slm-lab.gitbook.io/slm-lab/master/development/memory.md)
- [Replay](https://slm-lab.gitbook.io/slm-lab/master/development/memory/replay.md)
- [PrioritizedReplay](https://slm-lab.gitbook.io/slm-lab/master/development/memory/prioritizedreplay.md)
- [OnPolicyReplay](https://slm-lab.gitbook.io/slm-lab/master/development/memory/batch.md)
- [OnPolicyBatchReplay](https://slm-lab.gitbook.io/slm-lab/master/development/memory/episodic.md)
- [Net](https://slm-lab.gitbook.io/slm-lab/master/development/neural-networks.md)
- [MLP](https://slm-lab.gitbook.io/slm-lab/master/development/neural-networks/mlp.md)
- [CNN](https://slm-lab.gitbook.io/slm-lab/master/development/neural-networks/cnn.md)
- [RNN](https://slm-lab.gitbook.io/slm-lab/master/development/neural-networks/rnn.md)
- [Profiling SLM Lab](https://slm-lab.gitbook.io/slm-lab/master/development/profiling-slm-lab.md)
- [Book: Foundations of Deep Reinforcement Learning](https://slm-lab.gitbook.io/slm-lab/master/publications-and-talks/instruction-for-the-book-+-intro-to-rl-section.md)
- [Talks and Presentations](https://slm-lab.gitbook.io/slm-lab/master/publications-and-talks/talks-given-with-slm-lab.md)
- [Deep RL Resources](https://slm-lab.gitbook.io/slm-lab/master/resources/untitled.md)
- [Contributing](https://slm-lab.gitbook.io/slm-lab/master/resources/contributing.md)
- [Motivation](https://slm-lab.gitbook.io/slm-lab/master/resources/motivation.md)
- [Help](https://slm-lab.gitbook.io/slm-lab/master/resources/help.md)
- [Contact](https://slm-lab.gitbook.io/slm-lab/master/resources/contacts.md)

## v4.2.3

- [SLM Lab](https://slm-lab.gitbook.io/slm-lab/v4.2.3/master.md): Modular Deep Reinforcement Learning framework in PyTorch.
- [Installation](https://slm-lab.gitbook.io/slm-lab/v4.2.3/setup/installation.md)
- [Quick Start](https://slm-lab.gitbook.io/slm-lab/v4.2.3/setup/quick-start.md): To test the installation.
- [Lab Command](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/slm-lab-command.md)
- [Lab Organization](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/lab-organization.md)
- [Train: REINFORCE CartPole](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/train-and-enjoy-dqn-cartpole.md)
- [Resume and Enjoy: REINFORCE CartPole](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/resume-and-enjoy-reinforce-cartpole.md)
- [Agent Spec: DDQN+PER on LunarLander](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/agent-spec-ddqn+per-on-lunarlander.md)
- [Env Spec: A2C on Pong](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/environment-spec-a2c-on-bipedalwalker.md)
- [GPU Usage: PPO on Pong](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/gpu-usage-ppo-on-pong.md)
- [Parallelizing Training: Async SAC on Humanoid](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/parallelizing-training-async-sac-on-humanoid.md)
- [Experiment and Search Spec: PPO on Breakout](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/search-spec-ppo-on-breakout.md)
- [Run Benchmark: A2C on Atari Games](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/run-benchmark-a2c-on-atari-games.md)
- [Meta Spec: High Level Specifications](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/meta-spec-high-level-specifications.md)
- [Post-Hoc Analysis](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/post-hoc-analysis.md)
- [TensorBoard: Visualizing Models and Actions](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/tensorboard-visualizing-models-and-actions.md)
- [Using SLM Lab In Your Project](https://slm-lab.gitbook.io/slm-lab/v4.2.3/using-slm-lab/using-slm-lab-in-your-project.md)
- [Data Locations](https://slm-lab.gitbook.io/slm-lab/v4.2.3/analyzing-results/analytics.md)
- [Graphs and Data](https://slm-lab.gitbook.io/slm-lab/v4.2.3/analyzing-results/session-graph.md)
- [Performance Metrics](https://slm-lab.gitbook.io/slm-lab/v4.2.3/analyzing-results/performance-metrics.md)
- [Public Benchmark Data](https://slm-lab.gitbook.io/slm-lab/v4.2.3/benchmark-results/public-benchmark-data.md)
- [Discrete Environment Benchmark](https://slm-lab.gitbook.io/slm-lab/v4.2.3/benchmark-results/discrete-benchmark.md)
- [Continuous Environment Benchmark](https://slm-lab.gitbook.io/slm-lab/v4.2.3/benchmark-results/continuous-benchmark.md)
- [Atari Environment Benchmark](https://slm-lab.gitbook.io/slm-lab/v4.2.3/benchmark-results/atari-benchmark.md)
- [RL GIFs](https://slm-lab.gitbook.io/slm-lab/v4.2.3/benchmark-results/rl-gifs.md): A collection of replay GIFs generated from SLM Lab agents in "enjoy" mode.
- [Modular Design](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/modular-lab-components.md)
- [Algorithm Taxonomy](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/modular-lab-components/algorithm-taxonomy.md)
- [Class Inheritance: A2C > PPO](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/modular-lab-components/class-inheritance-a2c-greater-than-ppo.md)
- [Algorithm](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/algorithms.md)
- [DQN](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/algorithms/dqn.md)
- [REINFORCE](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/algorithms/reinforce.md)
- [Actor Critic](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/algorithms/a2c.md)
- [Memory](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/memory.md)
- [Replay](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/memory/replay.md)
- [PrioritizedReplay](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/memory/prioritizedreplay.md)
- [OnPolicyReplay](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/memory/batch.md)
- [OnPolicyBatchReplay](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/memory/episodic.md)
- [Net](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/neural-networks.md)
- [MLP](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/neural-networks/mlp.md)
- [CNN](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/neural-networks/cnn.md)
- [RNN](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/neural-networks/rnn.md)
- [Profiling SLM Lab](https://slm-lab.gitbook.io/slm-lab/v4.2.3/development/profiling-slm-lab.md)
- [Book: Foundations of Deep Reinforcement Learning](https://slm-lab.gitbook.io/slm-lab/v4.2.3/publications-and-talks/instruction-for-the-book-+-intro-to-rl-section.md)
- [Talks and Presentations](https://slm-lab.gitbook.io/slm-lab/v4.2.3/publications-and-talks/talks-given-with-slm-lab.md)
- [Deep RL Resources](https://slm-lab.gitbook.io/slm-lab/v4.2.3/resources/untitled.md)
- [Contributing](https://slm-lab.gitbook.io/slm-lab/v4.2.3/resources/contributing.md)
- [Motivation](https://slm-lab.gitbook.io/slm-lab/v4.2.3/resources/motivation.md)
- [Help](https://slm-lab.gitbook.io/slm-lab/v4.2.3/resources/help.md)
- [Contact](https://slm-lab.gitbook.io/slm-lab/v4.2.3/resources/contacts.md)

## v5.0.0

- [SLM Lab](https://slm-lab.gitbook.io/slm-lab/v5.0.0/readme.md): Modular Deep Reinforcement Learning framework in PyTorch.
- [Installation](https://slm-lab.gitbook.io/slm-lab/v5.0.0/setup/installation.md)
- [Quick Start](https://slm-lab.gitbook.io/slm-lab/v5.0.0/setup/quick-start.md): Test your installation with a quick demo.
- [Train: PPO on CartPole](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/train-ppo-cartpole.md)
- [Resume and Replay](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/resume-and-replay.md)
- [Core Concepts](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/lab-organization.md)
- [Agent Spec](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/agent-spec-ddqn+per-on-lunarlander.md)
- [Env Spec](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/environment-spec-a2c-on-bipedalwalker.md)
- [Meta Spec](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/meta-spec-high-level-specifications.md)
- [Search Spec](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/search-spec-ppo-on-breakout.md)
- [GPU Training](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/gpu-usage-ppo-on-pong.md)
- [Remote Training](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/remote-training.md)
- [Async Training: Hogwild!](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/async-training-a3c-hogwild.md)
- [Running Benchmarks](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/benchmark-specs.md)
- [CLI Reference](https://slm-lab.gitbook.io/slm-lab/v5.0.0/using-slm-lab/slm-lab-command.md)
- [Data Locations](https://slm-lab.gitbook.io/slm-lab/v5.0.0/analyzing-results/analytics.md)
- [Graphs and Data](https://slm-lab.gitbook.io/slm-lab/v5.0.0/analyzing-results/session-graph.md)
- [TensorBoard](https://slm-lab.gitbook.io/slm-lab/v5.0.0/analyzing-results/tensorboard-visualizing-models-and-actions.md)
- [Performance Metrics](https://slm-lab.gitbook.io/slm-lab/v5.0.0/analyzing-results/performance-metrics.md)
- [Post-Hoc Analysis](https://slm-lab.gitbook.io/slm-lab/v5.0.0/analyzing-results/post-hoc-analysis.md)
- [Public Benchmark Data](https://slm-lab.gitbook.io/slm-lab/v5.0.0/benchmark-results/public-benchmark-data.md)
- [Discrete Benchmark](https://slm-lab.gitbook.io/slm-lab/v5.0.0/benchmark-results/discrete-benchmark.md)
- [Continuous Benchmark](https://slm-lab.gitbook.io/slm-lab/v5.0.0/benchmark-results/continuous-benchmark.md)
- [Atari Benchmark](https://slm-lab.gitbook.io/slm-lab/v5.0.0/benchmark-results/atari-benchmark.md)
- [RL GIFs](https://slm-lab.gitbook.io/slm-lab/v5.0.0/benchmark-results/rl-gifs.md): Trained agents in action—watch SLM Lab's PPO and SAC algorithms play games and control robots.
- [Architecture](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/architecture.md)
- [Modular Design](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/modular-lab-components.md)
- [Algorithm Taxonomy](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/modular-lab-components/algorithm-taxonomy.md)
- [Class Inheritance: A2C > PPO](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/modular-lab-components/class-inheritance-a2c-greater-than-ppo.md)
- [Algorithm Families](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/algorithms.md)
- [DQN](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/algorithms/dqn.md)
- [REINFORCE](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/algorithms/reinforce.md)
- [Actor-Critic](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/algorithms/a2c.md)
- [Memory](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/memory.md)
- [Replay](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/memory/replay.md)
- [PrioritizedReplay](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/memory/prioritizedreplay.md)
- [OnPolicyReplay](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/memory/onpolicyreplay.md)
- [OnPolicyBatchReplay](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/memory/onpolicybatchreplay.md)
- [Net](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/neural-networks.md)
- [MLP](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/neural-networks/mlp.md)
- [CNN](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/neural-networks/cnn.md)
- [RNN](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/neural-networks/rnn.md)
- [Profiling SLM Lab](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/profiling-slm-lab.md)
- [Using SLM Lab In Your Project](https://slm-lab.gitbook.io/slm-lab/v5.0.0/development/using-slm-lab-in-your-project.md)
- [Book: Foundations of Deep RL](https://slm-lab.gitbook.io/slm-lab/v5.0.0/publications-and-talks/instruction-for-the-book-+-intro-to-rl-section.md)
- [Talks and Presentations](https://slm-lab.gitbook.io/slm-lab/v5.0.0/publications-and-talks/talks-given-with-slm-lab.md)
- [Deep RL Resources](https://slm-lab.gitbook.io/slm-lab/v5.0.0/resources/untitled.md)
- [Contributing](https://slm-lab.gitbook.io/slm-lab/v5.0.0/resources/contributing.md)
- [Code of Conduct](https://slm-lab.gitbook.io/slm-lab/v5.0.0/resources/code-of-conduct.md)
- [Motivation](https://slm-lab.gitbook.io/slm-lab/v5.0.0/resources/motivation.md)
- [Help](https://slm-lab.gitbook.io/slm-lab/v5.0.0/resources/help.md)
- [Contact](https://slm-lab.gitbook.io/slm-lab/v5.0.0/resources/contacts.md)
- [Changelog](https://slm-lab.gitbook.io/slm-lab/v5.0.0/resources/changelog.md)

## v5.1.0

- [SLM Lab](https://slm-lab.gitbook.io/slm-lab/v5.1.0/readme.md): Modular Deep Reinforcement Learning framework in PyTorch.
- [Installation](https://slm-lab.gitbook.io/slm-lab/v5.1.0/setup/installation.md)
- [Quick Start](https://slm-lab.gitbook.io/slm-lab/v5.1.0/setup/quick-start.md): Test your installation with a quick demo.
- [Train: PPO on CartPole](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/train-ppo-cartpole.md)
- [Resume and Replay](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/resume-and-replay.md)
- [Core Concepts](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/lab-organization.md)
- [Agent Spec](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/agent-spec-ddqn+per-on-lunarlander.md)
- [Env Spec](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/environment-spec-a2c-on-bipedalwalker.md)
- [Meta Spec](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/meta-spec-high-level-specifications.md)
- [Search Spec](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/search-spec-ppo-on-breakout.md)
- [GPU Training](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/gpu-usage-ppo-on-pong.md)
- [Remote Training](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/remote-training.md)
- [Async Training: Hogwild!](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/async-training-a3c-hogwild.md)
- [Running Benchmarks](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/benchmark-specs.md)
- [CLI Reference](https://slm-lab.gitbook.io/slm-lab/v5.1.0/using-slm-lab/slm-lab-command.md)
- [Data Locations](https://slm-lab.gitbook.io/slm-lab/v5.1.0/analyzing-results/analytics.md)
- [Graphs and Data](https://slm-lab.gitbook.io/slm-lab/v5.1.0/analyzing-results/session-graph.md)
- [TensorBoard](https://slm-lab.gitbook.io/slm-lab/v5.1.0/analyzing-results/tensorboard-visualizing-models-and-actions.md)
- [Performance Metrics](https://slm-lab.gitbook.io/slm-lab/v5.1.0/analyzing-results/performance-metrics.md)
- [Post-Hoc Analysis](https://slm-lab.gitbook.io/slm-lab/v5.1.0/analyzing-results/post-hoc-analysis.md)
- [Public Benchmark Data](https://slm-lab.gitbook.io/slm-lab/v5.1.0/benchmark-results/public-benchmark-data.md)
- [Discrete Benchmark](https://slm-lab.gitbook.io/slm-lab/v5.1.0/benchmark-results/discrete-benchmark.md)
- [Continuous Benchmark](https://slm-lab.gitbook.io/slm-lab/v5.1.0/benchmark-results/continuous-benchmark.md)
- [Atari Benchmark](https://slm-lab.gitbook.io/slm-lab/v5.1.0/benchmark-results/atari-benchmark.md)
- [RL GIFs](https://slm-lab.gitbook.io/slm-lab/v5.1.0/benchmark-results/rl-gifs.md): Trained agents in action—watch SLM Lab's PPO and SAC algorithms play games and control robots.
- [Architecture](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/architecture.md)
- [Modular Design](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/modular-lab-components.md)
- [Algorithm Taxonomy](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/modular-lab-components/algorithm-taxonomy.md)
- [Class Inheritance: A2C > PPO](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/modular-lab-components/class-inheritance-a2c-greater-than-ppo.md)
- [Algorithm Families](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/algorithms.md)
- [DQN](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/algorithms/dqn.md)
- [REINFORCE](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/algorithms/reinforce.md)
- [Actor-Critic](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/algorithms/a2c.md)
- [Memory](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/memory.md)
- [Replay](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/memory/replay.md)
- [PrioritizedReplay](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/memory/prioritizedreplay.md)
- [OnPolicyReplay](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/memory/onpolicyreplay.md)
- [OnPolicyBatchReplay](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/memory/onpolicybatchreplay.md)
- [Net](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/neural-networks.md)
- [MLP](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/neural-networks/mlp.md)
- [CNN](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/neural-networks/cnn.md)
- [RNN](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/neural-networks/rnn.md)
- [TorchArc](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/neural-networks/torcharc.md)
- [Profiling SLM Lab](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/profiling-slm-lab.md)
- [Using SLM Lab In Your Project](https://slm-lab.gitbook.io/slm-lab/v5.1.0/development/using-slm-lab-in-your-project.md)
- [Book: Foundations of Deep RL](https://slm-lab.gitbook.io/slm-lab/v5.1.0/publications-and-talks/instruction-for-the-book-+-intro-to-rl-section.md)
- [Talks and Presentations](https://slm-lab.gitbook.io/slm-lab/v5.1.0/publications-and-talks/talks-given-with-slm-lab.md)
- [Deep RL Resources](https://slm-lab.gitbook.io/slm-lab/v5.1.0/resources/untitled.md)
- [Contributing](https://slm-lab.gitbook.io/slm-lab/v5.1.0/resources/contributing.md)
- [Code of Conduct](https://slm-lab.gitbook.io/slm-lab/v5.1.0/resources/code-of-conduct.md)
- [Motivation](https://slm-lab.gitbook.io/slm-lab/v5.1.0/resources/motivation.md)
- [Help](https://slm-lab.gitbook.io/slm-lab/v5.1.0/resources/help.md)
- [Contact](https://slm-lab.gitbook.io/slm-lab/v5.1.0/resources/contacts.md)
- [Changelog](https://slm-lab.gitbook.io/slm-lab/v5.1.0/resources/changelog.md)

## v5.2.0

- [SLM Lab](https://slm-lab.gitbook.io/slm-lab/v5.2.0/readme.md): Modular Deep Reinforcement Learning framework in PyTorch.
- [Installation](https://slm-lab.gitbook.io/slm-lab/v5.2.0/setup/installation.md)
- [Quick Start](https://slm-lab.gitbook.io/slm-lab/v5.2.0/setup/quick-start.md): Test your installation with a quick demo.
- [Train: PPO on CartPole](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/train-ppo-cartpole.md)
- [Resume and Replay](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/resume-and-replay.md)
- [Core Concepts](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/lab-organization.md)
- [Agent Spec](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/agent-spec-ddqn+per-on-lunarlander.md)
- [Env Spec](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/environment-spec-a2c-on-bipedalwalker.md)
- [Meta Spec](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/meta-spec-high-level-specifications.md)
- [Search Spec](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/search-spec-ppo-on-breakout.md)
- [GPU Training](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/gpu-usage-ppo-on-pong.md)
- [Remote Training](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/remote-training.md)
- [Async Training: Hogwild!](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/async-training-a3c-hogwild.md)
- [Running Benchmarks](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/benchmark-specs.md)
- [CLI Reference](https://slm-lab.gitbook.io/slm-lab/v5.2.0/using-slm-lab/slm-lab-command.md)
- [Data Locations](https://slm-lab.gitbook.io/slm-lab/v5.2.0/analyzing-results/analytics.md)
- [Graphs and Data](https://slm-lab.gitbook.io/slm-lab/v5.2.0/analyzing-results/session-graph.md)
- [TensorBoard](https://slm-lab.gitbook.io/slm-lab/v5.2.0/analyzing-results/tensorboard-visualizing-models-and-actions.md)
- [Performance Metrics](https://slm-lab.gitbook.io/slm-lab/v5.2.0/analyzing-results/performance-metrics.md)
- [Post-Hoc Analysis](https://slm-lab.gitbook.io/slm-lab/v5.2.0/analyzing-results/post-hoc-analysis.md)
- [Public Benchmark Data](https://slm-lab.gitbook.io/slm-lab/v5.2.0/benchmark-results/public-benchmark-data.md)
- [Discrete Benchmark](https://slm-lab.gitbook.io/slm-lab/v5.2.0/benchmark-results/discrete-benchmark.md)
- [Continuous Benchmark](https://slm-lab.gitbook.io/slm-lab/v5.2.0/benchmark-results/continuous-benchmark.md)
- [Atari Benchmark](https://slm-lab.gitbook.io/slm-lab/v5.2.0/benchmark-results/atari-benchmark.md)
- [RL GIFs](https://slm-lab.gitbook.io/slm-lab/v5.2.0/benchmark-results/rl-gifs.md): Trained agents in action—watch SLM Lab's PPO and SAC algorithms play games and control robots.
- [Architecture](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/architecture.md)
- [Modular Design](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/modular-lab-components.md)
- [Algorithm Taxonomy](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/modular-lab-components/algorithm-taxonomy.md)
- [Class Inheritance: A2C > PPO](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/modular-lab-components/class-inheritance-a2c-greater-than-ppo.md)
- [Algorithm Families](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/algorithms.md)
- [DQN](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/algorithms/dqn.md)
- [REINFORCE](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/algorithms/reinforce.md)
- [Actor-Critic](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/algorithms/a2c.md)
- [PPO](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/algorithms/a2c/ppo.md)
- [SAC](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/algorithms/a2c/sac.md)
- [CrossQ](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/algorithms/a2c/crossq.md)
- [Memory](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/memory.md)
- [Replay](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/memory/replay.md)
- [PrioritizedReplay](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/memory/prioritizedreplay.md)
- [OnPolicyReplay](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/memory/onpolicyreplay.md)
- [OnPolicyBatchReplay](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/memory/onpolicybatchreplay.md)
- [Net](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/neural-networks.md)
- [MLP](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/neural-networks/mlp.md)
- [CNN](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/neural-networks/cnn.md)
- [RNN](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/neural-networks/rnn.md)
- [TorchArc](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/neural-networks/torcharc.md)
- [Profiling SLM Lab](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/profiling-slm-lab.md)
- [Using SLM Lab In Your Project](https://slm-lab.gitbook.io/slm-lab/v5.2.0/development/using-slm-lab-in-your-project.md)
- [Book: Foundations of Deep RL](https://slm-lab.gitbook.io/slm-lab/v5.2.0/publications-and-talks/instruction-for-the-book-+-intro-to-rl-section.md)
- [Talks and Presentations](https://slm-lab.gitbook.io/slm-lab/v5.2.0/publications-and-talks/talks-given-with-slm-lab.md)
- [Deep RL Resources](https://slm-lab.gitbook.io/slm-lab/v5.2.0/resources/untitled.md)
- [Contributing](https://slm-lab.gitbook.io/slm-lab/v5.2.0/resources/contributing.md)
- [Code of Conduct](https://slm-lab.gitbook.io/slm-lab/v5.2.0/resources/code-of-conduct.md)
- [Motivation](https://slm-lab.gitbook.io/slm-lab/v5.2.0/resources/motivation.md)
- [Help](https://slm-lab.gitbook.io/slm-lab/v5.2.0/resources/help.md)
- [Contact](https://slm-lab.gitbook.io/slm-lab/v5.2.0/resources/contacts.md)
- [Changelog](https://slm-lab.gitbook.io/slm-lab/v5.2.0/resources/changelog.md)

## v5.3.0

- [SLM Lab](https://slm-lab.gitbook.io/slm-lab/readme.md): Modular Deep Reinforcement Learning framework in PyTorch.
- [Installation](https://slm-lab.gitbook.io/slm-lab/setup/installation.md)
- [Quick Start](https://slm-lab.gitbook.io/slm-lab/setup/quick-start.md): Test your installation with a quick demo.
- [Train: PPO on CartPole](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/train-ppo-cartpole.md)
- [Resume and Replay](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/resume-and-replay.md)
- [Core Concepts](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/lab-organization.md)
- [Agent Spec](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/agent-spec-ddqn+per-on-lunarlander.md)
- [Env Spec](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/environment-spec-a2c-on-bipedalwalker.md)
- [Meta Spec](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/meta-spec-high-level-specifications.md)
- [Search Spec](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/search-spec-ppo-on-breakout.md)
- [GPU Training](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/gpu-usage-ppo-on-pong.md)
- [Remote Training](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/remote-training.md)
- [Async Training: Hogwild!](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/async-training-a3c-hogwild.md)
- [Running Benchmarks](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/benchmark-specs.md)
- [CLI Reference](https://slm-lab.gitbook.io/slm-lab/using-slm-lab/slm-lab-command.md)
- [Data Locations](https://slm-lab.gitbook.io/slm-lab/analyzing-results/analytics.md)
- [Graphs and Data](https://slm-lab.gitbook.io/slm-lab/analyzing-results/session-graph.md)
- [TensorBoard](https://slm-lab.gitbook.io/slm-lab/analyzing-results/tensorboard-visualizing-models-and-actions.md)
- [Performance Metrics](https://slm-lab.gitbook.io/slm-lab/analyzing-results/performance-metrics.md)
- [Post-Hoc Analysis](https://slm-lab.gitbook.io/slm-lab/analyzing-results/post-hoc-analysis.md)
- [Public Benchmark Data](https://slm-lab.gitbook.io/slm-lab/benchmark-results/public-benchmark-data.md)
- [Discrete Benchmark](https://slm-lab.gitbook.io/slm-lab/benchmark-results/discrete-benchmark.md)
- [Continuous Benchmark](https://slm-lab.gitbook.io/slm-lab/benchmark-results/continuous-benchmark.md)
- [Atari Benchmark](https://slm-lab.gitbook.io/slm-lab/benchmark-results/atari-benchmark.md)
- [Playground Benchmark](https://slm-lab.gitbook.io/slm-lab/benchmark-results/playground-benchmark.md)
- [RL GIFs](https://slm-lab.gitbook.io/slm-lab/benchmark-results/rl-gifs.md): Trained agents in action—watch SLM Lab's PPO and SAC algorithms play games and control robots.
- [Architecture](https://slm-lab.gitbook.io/slm-lab/development/architecture.md)
- [Modular Design](https://slm-lab.gitbook.io/slm-lab/development/modular-lab-components.md)
- [Algorithm Taxonomy](https://slm-lab.gitbook.io/slm-lab/development/modular-lab-components/algorithm-taxonomy.md)
- [Class Inheritance: A2C > PPO](https://slm-lab.gitbook.io/slm-lab/development/modular-lab-components/class-inheritance-a2c-greater-than-ppo.md)
- [Algorithm Families](https://slm-lab.gitbook.io/slm-lab/development/algorithms.md)
- [DQN](https://slm-lab.gitbook.io/slm-lab/development/algorithms/dqn.md)
- [REINFORCE](https://slm-lab.gitbook.io/slm-lab/development/algorithms/reinforce.md)
- [Actor-Critic](https://slm-lab.gitbook.io/slm-lab/development/algorithms/a2c.md)
- [PPO](https://slm-lab.gitbook.io/slm-lab/development/algorithms/a2c/ppo.md)
- [SAC](https://slm-lab.gitbook.io/slm-lab/development/algorithms/a2c/sac.md)
- [CrossQ](https://slm-lab.gitbook.io/slm-lab/development/algorithms/a2c/crossq.md)
- [Memory](https://slm-lab.gitbook.io/slm-lab/development/memory.md)
- [Replay](https://slm-lab.gitbook.io/slm-lab/development/memory/replay.md)
- [PrioritizedReplay](https://slm-lab.gitbook.io/slm-lab/development/memory/prioritizedreplay.md)
- [OnPolicyReplay](https://slm-lab.gitbook.io/slm-lab/development/memory/onpolicyreplay.md)
- [OnPolicyBatchReplay](https://slm-lab.gitbook.io/slm-lab/development/memory/onpolicybatchreplay.md)
- [Net](https://slm-lab.gitbook.io/slm-lab/development/neural-networks.md)
- [MLP](https://slm-lab.gitbook.io/slm-lab/development/neural-networks/mlp.md)
- [CNN](https://slm-lab.gitbook.io/slm-lab/development/neural-networks/cnn.md)
- [RNN](https://slm-lab.gitbook.io/slm-lab/development/neural-networks/rnn.md)
- [TorchArc](https://slm-lab.gitbook.io/slm-lab/development/neural-networks/torcharc.md)
- [Profiling SLM Lab](https://slm-lab.gitbook.io/slm-lab/development/profiling-slm-lab.md)
- [Using SLM Lab In Your Project](https://slm-lab.gitbook.io/slm-lab/development/using-slm-lab-in-your-project.md)
- [Book: Foundations of Deep RL](https://slm-lab.gitbook.io/slm-lab/publications-and-talks/instruction-for-the-book-+-intro-to-rl-section.md)
- [Talks and Presentations](https://slm-lab.gitbook.io/slm-lab/publications-and-talks/talks-given-with-slm-lab.md)
- [Deep RL Resources](https://slm-lab.gitbook.io/slm-lab/resources/untitled.md)
- [Contributing](https://slm-lab.gitbook.io/slm-lab/resources/contributing.md)
- [Code of Conduct](https://slm-lab.gitbook.io/slm-lab/resources/code-of-conduct.md)
- [Motivation](https://slm-lab.gitbook.io/slm-lab/resources/motivation.md)
- [Help](https://slm-lab.gitbook.io/slm-lab/resources/help.md)
- [Contact](https://slm-lab.gitbook.io/slm-lab/resources/contacts.md)
- [Changelog](https://slm-lab.gitbook.io/slm-lab/resources/changelog.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on a page URL with the `ask` query parameter:
```
GET https://slm-lab.gitbook.io/slm-lab/readme.md?ask=<question>
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.