mlsanityData to 7 Oct 2026

Multi-Agent Transfer Learning via Temporal Contrastive Learning

arXiv 2406.01377 ↗First posted 3 Jun 2024cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The approach involves pre-training a goal-conditioned agent, finetuning it on the target domain, and using contrastive learning to construct a planning graph that guides the agent via sub-goals. Experiments on multi-agent coordination Overcooked tasks demonstrate improved sample efficiency, the ability to solve sparse-reward and long-horizon problems, and enhanced interpretability compared to baselines. The results highlight the effectiveness of integrating goal-conditioned policies with unsupervised temporal abstraction learning for complex multi-agent transfer learning. Compared to state-of-the-art baselines, our method achieves the same or better performances while requiring only 21.7% of the training samples.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 40 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

36 of 40 references.

References · 36

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2016Progressive Neural Networkscited by 1,332
  6. 2017Hindsight Experience Replaycited by 1,096
  7. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  8. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  9. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  10. 2020Reinforcement Learning with Augmented Datacited by 452
  11. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 436
  12. 2016The Option-Critic Architecturecited by 433
24 more
  1. 2020Planning to Explore via Self-Supervised World Modelscited by 365
  2. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 345
  3. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
  4. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 259
  5. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
  6. 2019Go-Explore: a New Approach for Hard-Exploration Problemscited by 207
  7. 2019Skew-Fit: State-Covering Self-Supervised Reinforcement Learningcited by 171
  8. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 147
  9. 2018Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulationcited by 140
  10. 2021Discovering and Achieving Goals via World Modelscited by 131
  11. 2022Jump-Start Reinforcement Learningcited by 102
  12. 2017Meta Learning Shared Hierarchiescited by 93
  13. 2024Foundation Policies with Hilbert Representationscited by 89
  14. 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 84
  15. 2019Distilling Policy Distillationcited by 81
  16. 2018Kickstarting Deep Reinforcement Learningcited by 75
  17. 2016Deep Reinforcement Learning with Successor Features for Navigation across Similar Environmentscited by 50
  18. 2021AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scalecited by 43
  19. 2023Planning Goals for Explorationcited by 28
  20. 2020Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentationcited by 20
  21. 2023The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithmscited by 12
  22. 2021GenURL: A General Framework for Unsupervised Representation Learningcited by 6
  23. 2023Learning Sim-to-Real Dense Object Descriptors for Robotic Manipulationcited by 2
  24. 2023Reinforcement Learning for Picking Cluttered General Objects with Dense Object Descriptorscited by 1

Built on by

Not cited yet.