Offline Reinforcement Learning Research Survey

This video is a summary of offline reinforcement learning research up to last year (2023).
References:
A survey on offline reinforcement learning: Taxonomy, review, and open problems (2023)
ieeexplore.iee...
Offline Reinforcement Learning: BayLearn 2021 Keynote Talk (UA-cam video)
• Offline Reinforcement ...
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems (2020)
arxiv.org/pdf/...
OFFLINE RL FOR NATURAL LANGUAGE GENERATION WITH IMPLICIT LANGUAGE Q LEARNING (2023)
arxiv.org/pdf/...
A Minimalist Approach to Offline Reinforcement Learning (2021)
proceedings.ne...
COMBO: Conservative Offline Model-Based Policy Optimization (2021)
proceedings.ne...
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL (2021)
proceedings.ml...
BADGR: An Autonomous Self-Supervised Learning-Based Navigation System (2020)
ieeexplore.iee...
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions (2023)
proceedings.ml...
Leveraging Offline Data in Online Reinforcement Learning (2023)
proceedings.ml...
Direct preference optimization: Your language model is secretly a reward model (2023)
arxiv.org/pdf/...
Offline Reinforcement Learning as One Big Sequence Modeling Problem (2021)
proceedings.ne...
OFFLINE REINFORCEMENT LEARNING WITH IMPLICIT Q-LEARNING (2021)
arxiv.org/pdf/...
AWAC: Accelerating Online Reinforcement Learning with Offline Datasets (2021)
arxiv.org/pdf/...
COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning (2020)
arxiv.org/pdf/...
Conservative Q-Learning for Offline Reinforcement Learning (2020)
proceedings.ne...