Picture for Jinke He

Jinke He

Benchmarking Robustness and Generalization in Multi-Agent Systems: A Case Study on Neural MMO

Add code
Aug 30, 2023
Viaarxiv icon

What model does MuZero learn?

Add code
Jun 01, 2023
Viaarxiv icon

RangL: A Reinforcement Learning Competition Platform

Add code
Jul 28, 2022
Figure 1 for RangL: A Reinforcement Learning Competition Platform
Figure 2 for RangL: A Reinforcement Learning Competition Platform
Figure 3 for RangL: A Reinforcement Learning Competition Platform
Viaarxiv icon

Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems

Add code
Jul 01, 2022
Figure 1 for Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Figure 2 for Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Figure 3 for Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Figure 4 for Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Viaarxiv icon

Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems

Add code
Feb 03, 2022
Figure 1 for Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems
Figure 2 for Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems
Figure 3 for Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems
Figure 4 for Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems
Viaarxiv icon

Online Planning in POMDPs with Self-Improving Simulators

Add code
Jan 27, 2022
Figure 1 for Online Planning in POMDPs with Self-Improving Simulators
Figure 2 for Online Planning in POMDPs with Self-Improving Simulators
Figure 3 for Online Planning in POMDPs with Self-Improving Simulators
Figure 4 for Online Planning in POMDPs with Self-Improving Simulators
Viaarxiv icon

Influence-Augmented Online Planning for Complex Environments

Add code
Oct 21, 2020
Figure 1 for Influence-Augmented Online Planning for Complex Environments
Figure 2 for Influence-Augmented Online Planning for Complex Environments
Figure 3 for Influence-Augmented Online Planning for Complex Environments
Figure 4 for Influence-Augmented Online Planning for Complex Environments
Viaarxiv icon