7 papers
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…
Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration
Yun Qu, Boyuan Wang, Yuhang Jiang +7
With expansive state-action spaces, efficient multi-agent exploration remains a longstanding challenge in reinforcement learning. Although pursuing novelty, diversity, or uncertain…
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…
Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
Yun Qu, Boyuan Wang, Jianzhun Shao +15
The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected o…
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…