Learning Latent Representations To Influence Multi-agent Interaction

Abstract

Seamlessly interacting with humans or robots is hard because these agents are non-stationary. They update their policy in response to the ego agent's behavior, and the ego agent must anticipate these changes to co-adapt. Inspired by humans, we recognize that robots do not need to explicitly model every low-level action another agent will make; instead, we can capture the latent strategy of other agents through high-level representations. We propose a reinforcement learning-based framework for learning latent representations of an agent's policy, where the ego agent identifies the relationship between its behavior and the other agent's future strategy. The ego agent then leverages these latent dynamics to influence the other agent, purposely guiding them towards policies suitable for co-adaptation. Across several simulated domains and a real-world air hockey game, our approach outperforms the alternatives and learns to influence the other agent.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxie2020learning

Related papers

• Learning Policy Representations In Multiagent Systems (2018)0.00
• Ego-foresight: Self-supervised Learning Of Agent-aware Representations For Improved RL (2024)0.00
• Contrastive Learning-based Agent Modeling For Deep Reinforcement Learning (2023)0.00
• Multi-agent Deep Reinforcement Learning With Human Strategies (2018)8.09
• Real-world Human-robot Collaborative Reinforcement Learning (2020)9.41
• Metric Policy Representations For Opponent Modeling (2021)0.00
• Learning To Influence Human Behavior With Offline Reinforcement Learning (2023)0.00
• Learning Human Rewards By Inferring Their Latent Intelligence Levels In Multi-agent Games: A Theory-of-mind Approach With Application To Driving Data (2021)0.00