Portfolio ↗

Offline & Model-Based RL

Learning from logged data, distribution shift, conservative value estimation, world models and planning.

7concepts
72flashcards
51minutes of reading
Start with Decision Transformer and RL as Sequence Modelling Drill the deck
All levels beginner intermediate advanced
  1. 01 Decision Transformer and RL as Sequence Modelling Decision Transformer replaces value functions with a return-conditioned sequence model trained by supervised learning; it is stable and simple, and theory and benchmarks show it needs near-deterministic dynamics and cannot in general stitch suboptimal trajectories. intermediate 7m 7 cards