A Minimalist Approach to Offline Reinforcement Learning

arxiv:2106.06860

Original source · Paper JSON

Reinforcement learning · 2021-06-12

Cites (4) · Cited by (2)

Complete cleaned Markdown · Source Markdown including bibliography

Read in parts

1. Part 1
2. Part 2
3. Part 3

Contents

• A Minimalist Approach to Offline Reinforcement Learning
• Abstract
• 1 Introduction
• 2 Related Work
• 3 Background
• 4 Challenges in Offline RL
• 5 A Minimalist Offline RL Algorithm
• 6 Experiments
• 7 Conclusion
• Appendix A Broader Impact
• Appendix B Experimental Details
• Appendix C Additional Experiments
• C.1 Additional Datasets
• C.2 State Feature Normalization with Other Algorithms
• C.3 Benchmarking against the Decision Transformer
• Instructions for reporting errors