2307.08875
arxiv.org · 7,392 words · saved by 1 readers
N/A
Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation Ruida Zhou∗ Tao Liu∗ Min Cheng Texas A&M University Texas A&M University Texas A&M University ruida@tamu.edu tliu@tamu.edu minrara0404@tamu.edu arXiv:2307.08875v2 [cs.LG] 10 Dec 2023…
related reading
- [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
- [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
- Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc
- [2506.22401] Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLarxiv.org
- 2208.05129arxiv.org
- 1011.0686arxiv.org
- [2606.05555] Representation Learning Enables Scalable Multitask Deep Reinforcement Learningarxiv.org
- Exploration for the Efficient Deployment of Reinforcement Learning Agentsopenreview.net
- [2103.06326] S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningarxiv.org
- c21f4ce780c5c9d774f79841b81fdc6d-Paper.pdfproceedings.neurips.cc
- [2602.11399] Can We Really Learn One Representation to Optimize All Rewards?arxiv.org
- From REINFORCE to Dr. GRPOlancelqf.github.io