Equivariant Networks for Zero-Shot Coordination

• URL: http://arxiv.org/abs/2210.12124v2
• Date: Wed, 10 Apr 2024 11:45:10 GMT
• Title: Equivariant Networks for Zero-Shot Coordination
• Authors: Darius Muglich, Christian Schroeder de Witt, Elise van der Pol, Shimon Whiteson, Jakob Foerster,
• Abstract summary: Successful coordination in Dec-POMDPs requires agents to adopt robust strategies and interpretable styles of play for their partner. A common failure mode is symmetry breaking, when agents arbitrarily converge on one out of many equivalent but mutually incompatible policies. We present a novel equivariant network architecture for use in Dec-POMDPs that effectively leverages environmental symmetry for improving zero-shot coordination.
• Score: 34.95582850032728
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Successful coordination in Dec-POMDPs requires agents to adopt robust strategies and interpretable styles of play for their partner. A common failure mode is symmetry breaking, when agents arbitrarily converge on one out of many equivalent but mutually incompatible policies. Commonly these examples include partial observability, e.g. waving your right hand vs. left hand to convey a covert message. In this paper, we present a novel equivariant network architecture for use in Dec-POMDPs that effectively leverages environmental symmetry for improving zero-shot coordination, doing so more effectively than prior methods. Our method also acts as a ``coordination-improvement operator'' for generic, pre-trained policies, and thus may be applied at test-time in conjunction with any self-play algorithm. We provide theoretical guarantees of our work and test on the AI benchmark task of Hanabi, where we demonstrate our methods outperforming other symmetry-aware baselines in zero-shot coordination, as well as able to improve the coordination ability of a variety of pre-trained policies. In particular, we show our method can be used to improve on the state of the art for zero-shot coordination on the Hanabi benchmark.

Related papers

• AgentMixer: Multi-Agent Correlated Policy Factorization [39.041191852287525]
  We introduce textitstrategy modification to provide a mechanism for agents to correlate their policies. We present a novel framework, AgentMixer, which constructs the joint fully observable policy as a non-linear combination of individual partially observable policies. We show that AgentMixer converges to an $epsilon$-approximate Correlated Equilibrium.
  arXiv  Detail & Related papers  (2024-01-16T15:32:41Z)
• A Minimaximalist Approach to Reinforcement Learning from Human Feedback [49.45285664482369]
  We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training. We demonstrate that on a suite of continuous control tasks, we are able to learn significantly more efficiently than reward-model based approaches.
  arXiv  Detail & Related papers  (2024-01-08T17:55:02Z)
• Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination [36.33334853998621]
  We introduce the Cooperative Open-ended LEarning (COLE) framework to solve cooperative incompatibility in learning. COLE formulates open-ended objectives in cooperative games with two players using perspectives of graph theory to evaluate and pinpoint the cooperative capacity of each strategy. We show that COLE could effectively overcome the cooperative incompatibility from theoretical and empirical analysis.
  arXiv  Detail & Related papers  (2023-06-05T16:51:38Z)
• Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning [7.784991832712813]
  We introduce a Bayesian network to inaugurate correlations between agents' action selections in their joint policy. We develop practical algorithms to learn the context-aware Bayesian network policies. Empirical results on a range of MARL benchmarks show the benefits of our approach.
  arXiv  Detail & Related papers  (2023-06-02T21:22:27Z)
• Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning [17.101534531286298]
  We construct a Nash-level policy model based on a conditional hypernetwork shared by all agents. This approach allows for asymmetric training with symmetric execution, with each agent responding optimally conditioned on the decisions made by superior agents. Experiments demonstrate that our method effectively converges to the SE policies in repeated matrix game scenarios.
  arXiv  Detail & Related papers  (2023-04-20T14:47:54Z)
• K-level Reasoning for Zero-Shot Coordination in Hanabi [26.38814779896388]
  We show that we can obtain competitive ZSC and ad-hoc teamplay performance in Hanabi. We also introduce a new method, synchronous-k-level reasoning with a best response.
  arXiv  Detail & Related papers  (2022-07-14T18:53:34Z)
• RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning [55.55009081609396]
  We propose a novel method, called Relation-Aware Credit Assignment (RACA), which achieves zero-shot generalization in ad-hoc cooperation scenarios. RACA takes advantage of a graph-based encoder relation to encode the topological structure between agents. Our method outperforms baseline methods on the StarCraftII micromanagement benchmark and ad-hoc cooperation scenarios.
  arXiv  Detail & Related papers  (2022-06-02T03:39:27Z)
• Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
  This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
  arXiv  Detail & Related papers  (2021-12-03T19:23:48Z)
• A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning [122.49765136434353]
  We present an effective method, called Hamiltonian Monte Carlo with Accumulated Momentum (HMCAM), aiming to generate a sequence of adversarial examples. We also propose a new generative method called Contrastive Adversarial Training (CAT), which approaches equilibrium distribution of adversarial examples. Both quantitative and qualitative analysis on several natural image datasets and practical systems have confirmed the superiority of the proposed algorithm.
  arXiv  Detail & Related papers  (2020-10-15T16:07:26Z)
• Decentralized MCTS via Learned Teammate Models [89.24858306636816]
  We present a trainable online decentralized planning algorithm based on decentralized Monte Carlo Tree Search. We show that deep learning and convolutional neural networks can be employed to produce accurate policy approximators.
  arXiv  Detail & Related papers  (2020-03-19T13:10:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.