Learning to Cooperate with Unseen Agent via Meta-Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
Ad hoc teamwork problem describes situations where an agent has to cooperate with previously unseen agents to achieve a common goal. For an agent to be successful in these scenarios, it has to have a suitable cooperative skill. One could implement cooperative skills into an agent by using domain knowledge to design the agent's behavior. However, in complex domains, domain knowledge might not be available. Therefore, it is worthwhile to explore how to directly learn cooperative skills from data. In this work, we apply meta-reinforcement learning (meta-RL) formulation in the context of the ad hoc teamwork problem. Our empirical results show that such a method could produce robust cooperative agents in two cooperative environments with different cooperative circumstances: social compliance and language interpretation. (This is a full paper of the extended abstract version.)
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 5 Nov 2021.
Builds on
32 of 45 references.
References · 32
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
- 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
- 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
- 2018Learning Dexterous In-Hand Manipulationcited by 643
- 2019Meta-Learning with Implicit Gradientscited by 523
- 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
- 2016Learning to reinforcement learncited by 369
- 2020Planning to Explore via Self-Supervised World Modelscited by 365
20 more
- 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 345
- 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
- 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
- 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
- 2013The Complexity of Decentralized Control of Markov Decision Processescited by 225
- 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 194
- 2020"Other-Play" for Zero-Shot Coordinationcited by 194
- 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 180
- 2019Active Domain Randomizationcited by 161
- 2021Collaborating with Humans without Human Datacited by 139
- 2017Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problemscited by 126
- 2017Emergent Complexity via Multi-Agent Competitioncited by 117
- 2016Opponent Modeling in Deep Reinforcement Learningcited by 94
- 2019AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligencecited by 84
- 2017Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithmcited by 65
- 2018Modeling Others using Oneself in Multi-Agent Reinforcement Learningcited by 64
- 2018Learning Policy Representations in Multiagent Systemscited by 48
- 2018Unsupervised Meta-Learning for Reinforcement Learningcited by 38
- 2021On the Critical Role of Conventions in Adaptive Human-AI Collaborationcited by 26
- 2019Towards Deployment of Robust AI Agents for Human-Machine Partnershipscited by 3
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.