RL from Fixed Data
Learn from logged data.
Challenges
Distribution shift. Extrapolation error.
Methods
CQL. IQL. Conservative Q-learning.
Data
D4RL dataset. Batch RL.
Key Takeaways
- Offline RL from logged data
- Conservative Q-learning
- D4RL benchmarks
Offline Reinforcement Learning
Topic: Offline RL
Advertisement
Advertisement
Advertisement
Need More Practice?
Get personalized data science help from ChatWhole's AI-powered platform.
Get Expert Help →