Influencing Towards Stable Multi-Agent Interactions
arXiv:2110.08229
Abstract
Learning in multi-agent environments is difficult due to the non-stationarity introduced by an opponent's or partner's changing behaviors. Instead of reactively adapting to the other agent's (opponent or partner) behavior, we propose an algorithm to proactively influence the other agent's strategy to stabilize -- which can restrain the non-stationarity caused by the other agent. We learn a low-dimensional latent representation of the other agent's strategy and the dynamics of how the latent strategy evolves with respect to our robot's behavior. With this learned dynamics model, we can define an unsupervised stability reward to train our robot to deliberately influence the other agent to stabilize towards a single strategy. We demonstrate the effectiveness of stabilizing in improving efficiency of maximizing the task reward in a variety of simulated environments, including autonomous driving, emergent communication, and robotic manipulation. We show qualitative results on our website: https://sites.google.com/view/stable-marl/.
arXiv comment15 pages, 5 figures, Published as an Oral at Conference on Robot Learning (CoRL) 2021
References in corpus (8)
- Playing Atari with Deep Reinforcement Learning
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
- A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity
- On the Utility of Learning about Humans for Human-AI Coordination
- On the Critical Role of Conventions in Adaptive Human-AI Collaboration
- Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement Learning
- Learning to Incentivize Other Learning Agents