awesome-offline-rl
github.com/hanjuku-kaso/awesome-offline-rl ↗An index of algorithms for offline reinforcement learning (offline-rl)
1.1k
GitHub Stars
1.1k
Curated Resources
5
Categories
6 hours ago
Last Refreshed
PapersOpen Source Software/ImplementationsBlog/PodcastRelated WorkshopsTutorials/Talks/Lectures
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me offline rl: theory/methods resources from awesome-offline-rl"
Installation instructions →What's inside
Papers
- Accelerating exploration and representation learning with offline pre-trainingOffline RL: Theory/Methods
- Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of SimulationReview/Survey/Position Papers
- Accelerating Online Reinforcement Learning with Offline DatasetsOffline RL: Theory/Methods
- Accelerating Reinforcement Learning with Learned Skill PriorsOffline RL: Theory/Methods
- Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of ExamplesOffline RL: Theory/Methods
- Accountable Off-Policy Evaluation With Kernel Bellman StatisticsOff-Policy Evaluation and Learning: Theory/Methods
Tutorials/Talks/Lectures
- Adaptive Estimator Selection for Off-Policy Evaluation
- A Gentle Introduction to Offline Reinforcement Learning
- Batch RL Models Built for Validation
- Bellman-consistent Pessimism for Offline Reinforcement Learning
- Beyond the Training Distribution: Embodiment, Adaptation, and Symmetry
- Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism
Blog/Podcast
- AI Trends 2023: Reinforcement Learning – RLHF, Robotic Pre-Training, and Offline RL with Sergey LevinePodcast
- An Optimistic Perspective on Offline Reinforcement LearningBlog
- AWAC: Accelerating Online Reinforcement Learning with Offline DatasetsBlog
- Bandits and Simulators for Recommenders with Olivier JeunenPodcast
Open Source Software/Implementations
Related Workshops
Showing a sample of 1.1k resources. View the full list on GitHub →