research
∙
08/21/2023
Stabilizing Unsupervised Environment Design with a Learned Adversary
A key challenge in training generally-capable agents is the design of tr...
share
research
∙
06/16/2021
A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings
Society is characterized by the presence of a variety of social norms: c...
research
∙
03/02/2021
The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games
Proximal Policy Optimization (PPO) is a popular on-policy reinforcement ...
research
∙
12/03/2020
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
A wide range of reinforcement learning (RL) problems - including robustn...
research
∙
10/30/2020
Optimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous Vehicles and Multi-Agent RL
We study the ability of autonomous vehicles to improve the throughput of...
research
∙
08/04/2020
Robust Reinforcement Learning using Adversarial Populations
Reinforcement Learning (RL) is an effective tool for controller design b...
research
∙
12/27/2018
On the Approximability of Time Disjoint Walks
We introduce the combinatorial optimization problem Time Disjoint Walks....
research
∙
12/14/2018
Simulation to scaled city: zero-shot policy transfer for traffic control via autonomous vehicles
Using deep reinforcement learning, we train control policies for autonom...
research
∙
10/16/2017