SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.02249 · NeurIPS · 2022

Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning

Amos Storkey, Filippos Christianos, Lukas Schäfer, Stefano Albrecht

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Successful deployment of multi-agent reinforcement learning often requires agents to adapt their behaviour. In this work, we discuss the problem of teamwork adaptation in which a team of agents needs to adapt their policies to solve novel tasks with limited fine-tuning. Motivated by the intuition that agents need to be able to identify and distinguish tasks in order to adapt their behaviour to the current task, we propose to learn multi-agent task embeddings (MATE). These task embeddings are trained using an encoder-decoder architecture optimised for reconstruction of the transition and reward functions which uniquely identify tasks. We show that a team of agents is able to adapt to novel tasks when provided with task embeddings. We propose three MATE training paradigms: independent MATE, centralised MATE, and mixed MATE which vary in the information used for the task encoding. We show that the embeddings learned by MATE identify tasks and provide useful information which agents leverage during adaptation to novel tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.02249")
get_code_for_paper("2207.02249")
have("2207.02249")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.02249.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.02249.svg)](https://syntology.ai/paper/2207.02249)

Connect an agent — have() is free.