all AI news
Diffusion Reward: Learning Rewards via Conditional Video Diffusion
March 19, 2024, 4:44 a.m. | Tao Huang, Guangqi Jiang, Yanjie Ze, Huazhe Xu
cs.LG updates on arXiv.org arxiv.org
Abstract: Learning rewards from expert videos offers an affordable and effective solution to specify the intended behaviors for reinforcement learning tasks. In this work, we propose Diffusion Reward, a novel framework that learns rewards from expert videos via conditional video diffusion models for solving complex visual RL problems. Our key insight is that lower generative diversity is observed when conditioned on expert trajectories. Diffusion Reward is accordingly formalized by the negative of conditional entropy that encourages …
arxiv cs.cv cs.lg cs.ro diffusion type via video video diffusion
More from arxiv.org / cs.LG updates on arXiv.org
Testable Learning with Distribution Shift
1 day, 5 hours ago |
arxiv.org
Quantum circuit synthesis with diffusion models
1 day, 5 hours ago |
arxiv.org
Fitness Approximation through Machine Learning
1 day, 5 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Seeking Developers and Engineers for AI T-Shirt Generator Project
@ Chevon Hicks | Remote
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Senior Associate, Data and Analytics
@ Publicis Groupe | New York City, United States