Stabilizing RLHF through Advantage Model and Selective Rehearsal
Paper
•
2309.10202
•
Published
•
11
RLHF
-
-
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
Paper • 2309.10150 • Published • 25 -
Robotic Offline RL from Internet Videos via Value-Function Pre-Training
Paper • 2309.13041 • Published • 9 -
Voyager: An Open-Ended Embodied Agent with Large Language Models
Paper • 2305.16291 • Published • 11 -
Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
Paper • 2310.20587 • Published • 18 -
JaxMARL: Multi-Agent RL Environments in JAX
Paper • 2311.10090 • Published • 8 -
RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
Paper • 2312.00849 • Published • 12 -
RLVF: Learning from Verbal Feedback without Overgeneralization
Paper • 2402.10893 • Published • 12 -
Learning to Learn Faster from Human Feedback with Language Model Predictive Control
Paper • 2402.11450 • Published • 22 -
3D Diffusion Policy
Paper • 2403.03954 • Published • 14 -
Dataset Reset Policy Optimization for RLHF
Paper • 2404.08495 • Published • 9 -
Reward Steering with Evolutionary Heuristics for Decoding-time Alignment
Paper • 2406.15193 • Published • 15 -
WARP: On the Benefits of Weight Averaged Rewarded Policies
Paper • 2406.16768 • Published • 23 -
D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning
Paper • 2408.08441 • Published • 8 -
Reward-Robust RLHF in LLMs
Paper • 2409.15360 • Published • 6