Picture for Deheng Ye

Deheng Ye

Tencent Inc

MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind

Add code
Apr 25, 2025
Viaarxiv icon

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Add code
Apr 22, 2025
Viaarxiv icon

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

Add code
Mar 11, 2025
Viaarxiv icon

CORD: Generalizable Cooperation via Role Diversity

Add code
Jan 04, 2025
Figure 1 for CORD: Generalizable Cooperation via Role Diversity
Figure 2 for CORD: Generalizable Cooperation via Role Diversity
Figure 3 for CORD: Generalizable Cooperation via Role Diversity
Figure 4 for CORD: Generalizable Cooperation via Role Diversity
Viaarxiv icon

Playable Game Generation

Add code
Dec 01, 2024
Figure 1 for Playable Game Generation
Figure 2 for Playable Game Generation
Figure 3 for Playable Game Generation
Figure 4 for Playable Game Generation
Viaarxiv icon

Aligning Few-Step Diffusion Models with Dense Reward Difference Learning

Add code
Nov 18, 2024
Figure 1 for Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
Figure 2 for Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
Figure 3 for Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
Figure 4 for Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
Viaarxiv icon

Learning Versatile Skills with Curriculum Masking

Add code
Oct 23, 2024
Viaarxiv icon

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents

Add code
Oct 09, 2024
Figure 1 for WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Figure 2 for WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Figure 3 for WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Figure 4 for WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Viaarxiv icon

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

Add code
Aug 20, 2024
Figure 1 for Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
Figure 2 for Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
Figure 3 for Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
Figure 4 for Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
Viaarxiv icon

A Survey on Self-play Methods in Reinforcement Learning

Add code
Aug 02, 2024
Viaarxiv icon