paper-with-me

Papers

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

2021-12-22 · Rui Zhao, Jinming Song, Yufeng Yuan, Hu Haifeng, Yang Gao, Yi Wu, Zhongqian Sun, Yang Wei

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.

📄 PDF Abstract BibTeX arXiv:2112.11701

Code (3)

ruizhaogit/maximum_entropy_population_based_training 공식 구현 tf
PKU-Alignment/ProAgent pytorch
liyang619/cole-platform tf

Tasks

DiversityReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…

Similar Papers 제목 키워드 기반

MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection

2021-11-26 · Zhenhong Sun, Ming Lin, Xiuyu Sun, Zhiyu Tan 외

In object detection, the detection backbone consumes more than half of the overall inference cost. Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architectur…

GPUNeural Architecture SearchObjectobject-detection+1

Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning

2026-03-26 · Jiajun Hu, Nuria Armengol Urpi, Jin Cheng, Stelian Coros arxiv

Zero-shot reinforcement learning (RL) algorithms aim to learn a family of policies from a reward-free dataset, and recover optimal policies for any reward function directly at test time. Naturally, the quality of the pre…

Reinforcement Learning

Pairwise maximum-entropy models and their Glauber dynamics: bimodality, bistability, non-ergodicity problems, and their elimination via inhibition

2016-05-16

Pairwise maximum-entropy models have been used in recent neuroscientific literature to predict the activity of neuronal populations, given only the time-averaged correlations of the neuron activities. This paper provides…

A joint maximum-entropy model for binary neural population patterns and continuous signals

2009-12-01 · NeurIPS 2009 12 · Sebastian Gerwinn, Philipp Berens, Matthias Bethge

Second-order maximum-entropy models have recently gained much interest for describing the statistics of binary spike trains. Here, we extend this approach to take continuous stimuli into account as well. By constraining …

Maximum-entropy and representative samples of neuronal activity: a dilemma

2020-10-19

The present work shows that the maximum-entropy method can be applied to a sample of neuronal recordings along two different routes: (1) apply to the sample; or (2) apply to a larger, unsampled neuronal population from w…