Deheng Ye

8

Papers

12

Total Citations

Papers (8)

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Towards Playing Full MOBA Games with Deep Reinforcement Learning

Learning Diverse Policies in MOBA Games via Macro-Goals

Coordinated Proximal Policy Optimization

Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning

Mutual-Information Regularized Multi-Agent Policy Iteration

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks