Diffusion World Model
Paper
•
2402.03570
•
Published
•
7
RL
-
-
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
Paper • 2401.16335 • Published • 1 -
Towards Efficient and Exact Optimization of Language Model Alignment
Paper • 2402.00856 • Published -
ODIN: Disentangled Reward Mitigates Hacking in RLHF
Paper • 2402.07319 • Published • 13 -
Preference-free Alignment Learning with Regularized Relevance Reward
Paper • 2402.03469 • Published -
Teaching Large Language Models to Reason with Reinforcement Learning
Paper • 2403.04642 • Published • 43 -
RewardBench: Evaluating Reward Models for Language Modeling
Paper • 2403.13787 • Published • 18 -
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Paper • 2403.10704 • Published • 55 -
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
Paper • 2403.03950 • Published • 11 -
In deep reinforcement learning, a pruned network is a good network
Paper • 2402.12479 • Published • 16 -
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 58 -
Learn Your Reference Model for Real Good Alignment
Paper • 2404.09656 • Published • 80 -
Offline Regularised Reinforcement Learning for Large Language Models Alignment
Paper • 2405.19107 • Published • 7