会员服务
STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training
Arxiv
0+阅读 · 6月16日
Robust Conformal CBF and CLF Controllers via Iterative Policy Updates
Arxiv
0+阅读 · 6月13日
NCCLbpf: Verified, Composable Policy Execution for GPU Collective Communication
Arxiv
0+阅读 · 5月4日
SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning
Arxiv
0+阅读 · 4月10日
Polaris: A Gödel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair
Arxiv
0+阅读 · 3月24日
SSPO: Subsentence-level Policy Optimization
Arxiv
0+阅读 · 4月10日
Rewards as Labels: Revisiting RLVR from a Classification Perspective
Arxiv
0+阅读 · 3月9日
NCCLbpf: Verified, Composable Policy Execution for GPU Collective Communication
Arxiv
0+阅读 · 3月12日
Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
Arxiv
0+阅读 · 2月20日
Trust Regions Sell, But Who's Buying? Overlap Geometry as an Alternative Trust Region for Policy Optimization
Arxiv
0+阅读 · 2月6日
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
Arxiv
0+阅读 · 2月6日
Rewards as Labels: Revisiting RLVR from a Classification Perspective
Arxiv
0+阅读 · 2月5日
Deep SPI: Safe Policy Improvement via World Models
Arxiv
0+阅读 · 1月28日
Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action
Arxiv
0+阅读 · 1月27日
Projected Microbatch Accumulation yields reference-free proximal policy updates for reinforcement learning
Arxiv
0+阅读 · 1月15日
参考链接
微信扫码咨询专知VIP会员
Top