Reinforcement learning · MLD-1021
Replay buffer
Stored interaction data sampled again during training.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Reuse past state-action transitions.
Original caveat
Old data can differ from the current policy or environment.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: RL · DL · SLM · LLM.
Aliases: Experience replay.
Related concepts
Concepts linking here
Original references
- OpenAI Spinning Up: reinforcement learning ↗ · Consulted
- TRL documentation ↗ · Consulted
- Original reference URL ↗