Picture for Michael Matthews

Michael Matthews

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

Add code
Oct 30, 2024
Viaarxiv icon

JaxLife: An Open-Ended Agentic Simulator

Add code
Sep 01, 2024
Viaarxiv icon

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning

Add code
Feb 26, 2024
Viaarxiv icon

Refining Minimax Regret for Unsupervised Environment Design

Add code
Feb 19, 2024
Viaarxiv icon

Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning

Add code
Jul 23, 2022
Figure 1 for Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Figure 2 for Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Figure 3 for Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Figure 4 for Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Viaarxiv icon

TwitterPaul: Extracting and Aggregating Twitter Predictions

Add code
Nov 30, 2012
Figure 1 for TwitterPaul: Extracting and Aggregating Twitter Predictions
Figure 2 for TwitterPaul: Extracting and Aggregating Twitter Predictions
Figure 3 for TwitterPaul: Extracting and Aggregating Twitter Predictions
Figure 4 for TwitterPaul: Extracting and Aggregating Twitter Predictions
Viaarxiv icon