Reinforcement learning · MLD-1077
SARSA
An on-policy TD method updating action values using the action actually selected next.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Learn values under an exploratory policy.
Original caveat
Its target differs from Q-learning's greedy target.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: RL · DL · SLM · LLM.
Aliases: State-action-reward-state-action.
Related concepts
Original references
- OpenAI Spinning Up: reinforcement learning ↗ · Consulted
- TRL documentation ↗ · Consulted
- Original reference URL ↗