Supplemental practical concepts · MLD-0350
Effective horizon
The time range over which future outcomes materially influence a decision or learning objective.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Reason about long-delayed reward effects.
Original caveat
There is no universal horizon independent of task and discounting.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Evaluation.
Tags: ML · DL · LLM · SLM.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- Transformers glossary ↗ · Consulted
- OpenAI Spinning Up: reinforcement learning ↗ · Consulted
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗