reinforcement_learning.md

Reinforcement Learning

• Reinforcement Learning
  • Sample Efficiency
  • Offline RL
  • Imitation Learning
  • Model-based RL
  • Multi-Task RL
  • Language

Sample Efficiency

• ICLR 2023, Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
• ICLR 2023, Hybrid RL: Using both offline and online data can make RL efficient
• arXiv 2023, RLPD: Efficient Online Reinforcement Learning with Offline Data
• ICLR 2021, REDQ: Randomized Ensembled Double Q-Learning: Learning Fast Without a Model
• NIPS 2017, HER: Hindsight Experience Replay

Offline RL

• ICLR 2023, X-QL: Extreme Q-Learning: MaxEnt RL without Entropy, Website
• ICLR 2023, Diffusion-QL: Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning, OpenReview
• ICLR 2022, IQL: Offline Reinforcement Learning with Implicit Q-Learning, arXiv
• NIPS 2021, Decision Transformer: Reinforcement Learning via Sequence Modeling, Website
• NIPS 2020, CQL: Conservative Q-Learning for Offline Reinforcement Learning, Website
• ICLR 2021 rejection, D4RL: Datasets for Deep Data-Driven Reinforcement Learning

Imitation Learning

• NIPS 2016, GAIL: Generative adversarial imitation learning

Model-based RL

• arXiv 2023, Predictable MDP Abstraction for Unsupervised Model-Based RL
• ICML 2022, TD-MPC: Temporal Difference Learning for Model Predictive Control

Multi-Task RL

• ICML 2021, CARE: Multi-Task Reinforcement Learning with Context-based Representations
• NIPS 2020, Multi-Task Reinforcement Learning with Soft Modularization

Language

• arXiv 2022, Can Wikipedia Help Offline Reinforcement Learning?
• arXiv 2023, The Wisdom of Hindsight Makes Language Models Better Instruction Followers
• NIPS 2022, Pre-Trained Language Models for Interactive Decision-Making
• CoRL 2022, SayCan: Do As I Can, Not As I Say: Grounding Language in Robotic Affordances