mlsanityData to 7 Oct 2026

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

arXiv 2207.02249 ↗First posted 5 Jul 2022cs.MA cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 5 Jul 2022.

Builds on

36 of 53 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  8. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  9. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  10. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  12. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
24 more
  1. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  2. 2019Solving Rubik's Cube with a Robot Handcited by 699
  3. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  4. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  5. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
  6. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  7. 2016Learning to reinforcement learncited by 369
  8. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 257
  9. 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 210
  10. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 207
  11. 2020"Other-Play" for Zero-Shot Coordinationcited by 194
  12. 2017Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observabilitycited by 143
  13. 2017Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problemscited by 126
  14. 2020Shared Experience Actor-Critic for Multi-Agent Reinforcement Learningcited by 114
  15. 2020Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifierscited by 93
  16. 2019Meta-Q-Learningcited by 62
  17. 2020Agent Modelling under Partial Observability for Deep Reinforcement Learningcited by 56
  18. 2015A Game-Theoretic Model and Best-Response Learning Method for Ad Hoc Coordination in Multiagent Systemscited by 41
  19. 2021UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformerscited by 39
  20. 2020Towards Open Ad Hoc Teamwork Using Graph-based Policy Learningcited by 37
  21. 2021Deep Interactive Bayesian Reinforcement Learning via Meta-Learningcited by 29
  22. 2022Generalization in Cooperative Multi-Agent Systemscited by 18
  23. 2019Options as responses: Grounding behavioural hierarchies in multi-agent RLcited by 7
  24. 2021Learning Meta Representations for Agents in Multi-Agent Reinforcement Learningcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 0; 2025: 1.

5 papers.

  1. 2022Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversitycited by 17
  2. 2022Deep Reinforcement Learning for Multi-Agent Interactioncited by 3
  3. 2023Learning Embeddings for Sequential Tasks Using Population of Agentscited by 0
  4. 2023Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Makingcited by 0
  5. 2025Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Reviewcited by 0