Pith. sign in

REVIEW

Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2112.11701 v3 pith:VKXWDGEI submitted 2021-12-22 cs.AI

Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination

classification cs.AI
keywords trainingagentsdiversityentropyhumanspopulationpopulation-basedagent
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data. Although such agents can be obtained through self-play training, they can suffer significantly from distributional shift when paired with unencountered partners, such as humans. To mitigate this distributional shift, we propose Maximum Entropy Population-based training (MEP). In MEP, agents in the population are trained with our derived Population Entropy bonus to promote both pairwise diversity between agents and individual diversity of agents themselves, and a common best agent is trained by paring with agents in this diversified population via prioritized sampling. The prioritization is dynamically adjusted based on the training progress. We demonstrate the effectiveness of our method MEP, with comparison to Self-Play PPO (SP), Population-Based Training (PBT), Trajectory Diversity (TrajeDi), and Fictitious Co-Play (FCP) in the Overcooked game environment, with partners being human proxy models and real humans. A supplementary video showing experimental results is available at https://youtu.be/Xh-FKD0AAKE.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.