On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
"策略梯度" 相关文章
扩散语言模型也能强化学习？Meta田渊栋团队用“三明治梯度”打通RL闭环
A Prospect-Theoretic Policy Gradient Framework for Behaviorally Nuanced Reinforcement Learning
NeurIPS 2025 | CMU、清华、UTAustin开源ReinFlow，用在线RL微调机器人流匹配策略
NeurIPS 2025 | CMU、清华、UTAustin开源ReinFlow，用在线RL微调机器人流匹配策略
扩散语言模型也能强化学习？Meta田渊栋团队用“三明治梯度”打通RL闭环
扩散语言模型也能强化学习？Meta田渊栋团队用“三明治梯度”打通RL闭环
Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
Principled and Tractable RL for Reasoning with Diffusion Language Models
Reinforcement Learning for Recommendations and Search
Autonomous Vehicle Controllers From End-to-End Differentiable Simulation
Bridging Discrete and Continuous RL: Stable Deterministic Policy Gradient with Martingale Characterization
Continuous-Time Reinforcement Learning for Asset-Liability Management
C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning
Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
In continuous action spaces, how is the standard deviation, associated with Gaussian distribution from which actions are sampled, represented?
Implementing Deep Reinforcement Learning Models with Tensorflow + OpenAI Gym
Policy Gradient Algorithms
Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm
谁在拖慢你的RL？别怪显卡，错的可能是你的PG-loss
