activity
20242026
collaborators

6 papers

cs.LG2026

Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design

Leon Eshuijs, Shihan Wang, Antske Fokkens

Specification gaming under Reinforcement Learning (RL) is known to cause LLMs to develop sycophantic, manipulative, or deceptive behavior, yet the conditions under which this occur…

cs.AI2026

Neuro-symbolic Action Masking for Deep Reinforcement Learning

Shuai Han, Mehdi Dastani, Shihan Wang

Deep reinforcement learning (DRL) may explore infeasible actions during training and execution. Existing approaches assume a symbol grounding function that maps high-dimensional st…

cs.MA2025

Learning Communication Skills in Multi-task Multi-agent Deep Reinforcement Learning

Changxi Zhu, Mehdi Dastani, Shihan Wang

In multi-agent deep reinforcement learning (MADRL), agents can communicate with one another to perform a task in a coordinated manner. When multiple tasks are involved, agents can…

cs.LG2025

Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning

Shuai Han, Mehdi Dastani, Shihan Wang

Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL). Without clear feedback on actions at each step in…

cs.LG2025

Reducing Variance Caused by Communication in Decentralized Multi-agent Deep Reinforcement Learning

Changxi Zhu, Mehdi Dastani, Shihan Wang

In decentralized multi-agent deep reinforcement learning (MADRL), communication can help agents to gain a better understanding of the environment to better coordinate their behavio…

cs.MA2024

A Survey of Multi-Agent Deep Reinforcement Learning with Communication

Changxi Zhu, Mehdi Dastani, Shihan Wang

Communication is an effective mechanism for coordinating the behaviors of multiple agents, broadening their views of the environment, and to support their collaborations. In the fi…