5 citations · 14 across the 12 of their papers we have counts for
7 papers · 1 filter
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
Heming Zou, Qi Wang, Yun Qu +9
Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive poli…
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
Yun Qu, Qi Wang, Yixiu Mao +11
Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existin…
Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
Yun Qu, Yuhang Jiang, Boyuan Wang +4
Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in…
Doubly Mild Generalization for Offline Reinforcement Learning
Yixiu Mao, Qi Wang, Yun Qu +2
Offline Reinforcement Learning (RL) suffers from the extrapolation error and value overestimation. From a generalization perspective, this issue can be attributed to the over-gener…
Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning
Zihan Zhang, Yuhang Jiang, Yuan Zhou +1
In this paper, we study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. The mu…
Reducing Conservativeness Oriented Offline Reinforcement Learning
Hongchang Zhang, Jianzhun Shao, Yuhang Jiang +2
In offline reinforcement learning, a policy learns to maximize cumulative rewards with a fixed collection of data. Towards conservative strategy, current methods choose to regulari…
Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning
Jianzhun Shao, Hongchang Zhang, Yuhang Jiang +2
Reward decomposition is a critical problem in centralized training with decentralized execution~(CTDE) paradigm for multi-agent reinforcement learning. To take full advantage of gl…