Reinforcement learning · MLD-0316
Discount factor
A factor controlling how future rewards contribute to a return.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Weight rewards one step ahead by gamma.
Original caveat
Discounting can be mathematical, computational, or preference-motivated.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: RL · DL · SLM · LLM.
Aliases: Gamma (RL).
Related concepts
Concepts linking here
Original references
- OpenAI Spinning Up: reinforcement learning ↗ · Consulted
- TRL documentation ↗ · Consulted
- Original reference URL ↗