SLM Lab

Searchâ€¦

v4.2.3

ðŸ–¥Setup

ðŸš€Using SLM Lab

ðŸ“ˆAnalyzing Results

ðŸ¥‡Benchmark Results

ðŸ”§Development

ðŸ“–Publications and Talks

ðŸ¤“Resources

Algorithm Taxonomy

â€‹ Algorithm Taxonomy

ðŸŒ¿

Deep RL algorithms can be classified into a family tree based on their methods / functions they learn, such as the one shown below.

Source: Foundations of Deep Reinforcement Learning, Graesser & Keng.

Algorithms often extends an existing one by modifying or adding components. Most model-free algorithms are descended from SARSA and REINFORCE. The figure below shows some of the algorithms in SLM Lab, and their relationships.

Source: Foundations of Deep Reinforcement Learning, Graesser & Keng.

Naturally, implementations can be consistent with this theoretical taxonomy by using **class inheritance** and **modular components**. This is precisely what SLM Lab does.

Last modified 1mo ago

Copy link