Searching with Opponent-Awareness

04/21/2021
by   Timy Phan, et al.
0

We propose Searching with Opponent-Awareness (SOA), an approach to leverage opponent-aware planning without explicit or a priori opponent models for improving performance and social welfare in multi-agent systems. To this end, we develop an opponent-aware MCTS scheme using multi-armed bandits based on Learning with Opponent-Learning Awareness (LOLA) and compare its effectiveness with other bandits, including UCB1. Our evaluations include several different settings and show the benefits of SOA are especially evident with increasing number of agents.

READ FULL TEXT
research
05/30/2023

Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits

The study of collaborative multi-agent bandits has attracted significant...
research
01/26/2023

Collaborative Regret Minimization in Multi-Armed Bandits

In this paper, we study the collaborative learning model, which concerns...
research
07/07/2020

Robust Multi-Agent Multi-Armed Bandits

There has been recent interest in collaborative multi-agent bandits, whe...
research
11/14/2018

Partial Awareness

We develop a modal logic to capture partial awareness. The logic has thr...
research
09/26/2021

LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates

In cooperative multi-agent reinforcement learning (MARL), where agents o...
research
10/26/2015

A Parallel algorithm for X-Armed bandits

The target of X-armed bandit problem is to find the global maximum of an...
research
07/11/2023

Implicit Knowledge in Unawareness Structures – Extended Abstract

Awareness structures by Fagin and Halpern (1988) (FH) feature a syntacti...

Please sign up or login with your details

Forgot password? Click here to reset