7 citations · 8 across the 12 of their papers we have counts for
7 papers · 1 filter
A Unified Framework for Rethinking Policy Divergence Measures in GRPO
Qingyuan Wu, Yuhui Wang, Simon Sinong Zhan +6
Reinforcement Learning with Verified Reward (RLVR) has emerged as a critical paradigm for advancing the reasoning capabilities of Large Language Models (LLMs). Most existing RLVR m…
Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
Bowen Ding, Yuhan Chen, Jiayang Lyv +9
Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ fundamentally in their reliance on expert t…
Directly Forecasting Belief for Reinforcement Learning with Delays
Qingyuan Wu, Yuhui Wang, Simon Sinong Zhan +6
Reinforcement learning (RL) with delays is challenging as sensory perceptions lag behind the actual events: the RL agent needs to estimate the real state of its environment based o…
Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization
Simon Sinong Zhan, Qingyuan Wu, Philip Wang +4
Offline-to-online deployment of reinforcement-learning (RL) agents must bridge two gaps: (1) the sim-to-real gap, where real systems add latency and other imperfections not present…
Inverse Delayed Reinforcement Learning
Simon Sinong Zhan, Qingyuan Wu, Zhian Ruan +6
Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding feat…
Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping
Simon Sinong Zhan, Philip Wang, Qingyuan Wu +4
In this paper, we aim to tackle the limitation of the Adversarial Inverse Reinforcement Learning (AIRL) method in stochastic environments where theoretical results cannot hold and…
Variational Delayed Policy Optimization
Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang +5
In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning…