会员服务
On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
Arxiv
0+阅读 · 2月19日
ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm
Arxiv
0+阅读 · 2月10日
ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
Arxiv
0+阅读 · 2月13日
Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification
Arxiv
0+阅读 · 2月8日
Efficient and Sharp Off-Policy Learning under Unobserved Confounding
Arxiv
0+阅读 · 2月12日
Functional Critics Are Essential for Actor-Critic: From Off-Policy Stability to Efficient Exploration
Arxiv
0+阅读 · 2月8日
Additive Control Variates Dominate Self-Normalisation in Off-Policy Evaluation
Arxiv
0+阅读 · 2月16日
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Arxiv
0+阅读 · 2月11日
Stochastic Decision Horizons for Constrained Reinforcement Learning
Arxiv
0+阅读 · 2月4日
Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
Arxiv
0+阅读 · 2月3日
Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization
Arxiv
0+阅读 · 2月3日
DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects
Arxiv
0+阅读 · 2月1日
Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
Arxiv
0+阅读 · 1月26日
Off Policy Lyapunov Stability in Reinforcement Learning
Arxiv
0+阅读 · 1月16日
A Unifying View of Coverage in Linear Off-Policy Evaluation
Arxiv
0+阅读 · 1月26日
参考链接
微信扫码咨询专知VIP会员
Top