In deep reinforcement learning, a pruned network is a good network
Paper
•
2402.12479
•
Published
•
19
reinforcement learning
-
-
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
Paper • 2403.03950 • Published • 15 -
RLHF Workflow: From Reward Modeling to Online RLHF
Paper • 2405.07863 • Published • 71 -
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Paper • 2405.11143 • Published • 40 -
Understanding and Diagnosing Deep Reinforcement Learning
Paper • 2406.16979 • Published • 10 -
Efficient World Models with Context-Aware Tokenization
Paper • 2406.19320 • Published • 8 -
It Takes Two: Your GRPO Is Secretly DPO
Paper • 2510.00977 • Published • 31 -
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Paper • 2510.25992 • Published • 45