Picture for Mehdi Dastani

Mehdi Dastani

Optimal Causal Representations and the Causal Information Bottleneck

Add code
Oct 02, 2024
Viaarxiv icon

Maximally Permissive Reward Machines

Add code
Aug 15, 2024
Viaarxiv icon

Cooperative Multi-agent Approach for Automated Computer Game Testing

Add code
May 18, 2024
Figure 1 for Cooperative Multi-agent Approach for Automated Computer Game Testing
Figure 2 for Cooperative Multi-agent Approach for Automated Computer Game Testing
Figure 3 for Cooperative Multi-agent Approach for Automated Computer Game Testing
Figure 4 for Cooperative Multi-agent Approach for Automated Computer Game Testing
Viaarxiv icon

Fundamental Properties of Causal Entropy and Information Gain

Add code
Feb 02, 2024
Viaarxiv icon

Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks

Add code
Jan 25, 2024
Viaarxiv icon

Causal Entropy and Information Gain for Measuring Causal Control

Add code
Sep 14, 2023
Viaarxiv icon

Providing personalized Explanations: a Conversational Approach

Add code
Jul 21, 2023
Viaarxiv icon

Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization

Add code
May 05, 2023
Viaarxiv icon

A Survey of Multi-Agent Reinforcement Learning with Communication

Add code
Mar 16, 2022
Figure 1 for A Survey of Multi-Agent Reinforcement Learning with Communication
Figure 2 for A Survey of Multi-Agent Reinforcement Learning with Communication
Figure 3 for A Survey of Multi-Agent Reinforcement Learning with Communication
Figure 4 for A Survey of Multi-Agent Reinforcement Learning with Communication
Viaarxiv icon

The Complexity of Data-Driven Norm Synthesis and Revision

Add code
Dec 05, 2021
Viaarxiv icon