34 citations · 39 across the 9 of their papers we have counts for
9 papers
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…
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…
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…
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…
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…
Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks
Shuai Han, Mehdi Dastani, Shihan Wang
Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify rewa…
Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization
Yangyang Zhao, Zhenyu Wang, Mehdi Dastani +1
Training a dialogue policy using deep reinforcement learning requires a lot of exploration of the environment. The amount of wasted invalid exploration makes their learning ineffic…
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…
Using Cognitive Models to Train Warm Start Reinforcement Learning Agents for Human-Computer Interactions
Chao Zhang, Shihan Wang, Henk Aarts +1
Reinforcement learning (RL) agents in human-computer interactions applications require repeated user interactions before they can perform well. To address this "cold start" problem…