Modeling Others using Oneself in Multi-Agent Reinforcement Learning

02/26/2018
by   Roberta Raileanu, et al.
0

We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must infer the other players' hidden goals from their observed behavior in order to solve the tasks. We propose a new approach for learning in these domains: Self Other-Modeling (SOM), in which an agent uses its own policy to predict the other agent's actions and update its belief of their hidden state in an online manner. We evaluate this approach on three different tasks and show that the agents are able to learn better policies using their estimate of the other players' hidden states, in both cooperative and adversarial settings.

READ FULL TEXT
01/24/2019

Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning

We investigate how reinforcement learning agents can learn to cooperate....
07/20/2021

Learning Altruistic Behaviours in Reinforcement Learning without External Rewards

Can artificial agents learn to assist others in achieving their goals wi...
09/19/2018

Prosocial or Selfish? Agents with different behaviors for Contract Negotiation using Reinforcement Learning

We present an effective technique for training deep learning agents capa...
09/29/2018

M^3RL: Mind-aware Multi-agent Management Reinforcement Learning

Most of the prior work on multi-agent reinforcement learning (MARL) achi...
08/15/2013

Computational Rationalization: The Inverse Equilibrium Problem

Modeling the purposeful behavior of imperfect agents from a small number...
09/18/2019

Robust Opponent Modeling via Adversarial Ensemble Reinforcement Learning in Asymmetric Imperfect-Information Games

This paper presents an algorithmic framework for learning robust policie...
03/12/2019

Imitation Learning of Factored Multi-agent Reactive Models

We apply recent advances in deep generative modeling to the task of imit...