AILGJun 1, 2023

EMOTE: An Explainable architecture for Modelling the Other Through Empathy

arXiv:2306.00295v11 citationsh-index: 31
Originality Incremental advance
AI Analysis

This addresses the challenge of predicting fixed-policy agents in multi-agent scenarios, offering an incremental improvement with interpretability benefits.

The paper tackled the problem of modeling other agents' behaviors in multi-agent games by introducing an explainable architecture inspired by empathy, which improved performance in various environment configurations and produced human-interpretable states.

We can usually assume others have goals analogous to our own. This assumption can also, at times, be applied to multi-agent games - e.g. Agent 1's attraction to green pellets is analogous to Agent 2's attraction to red pellets. This "analogy" assumption is tied closely to the cognitive process known as empathy. Inspired by empathy, we design a simple and explainable architecture to model another agent's action-value function. This involves learning an "Imagination Network" to transform the other agent's observed state in order to produce a human-interpretable "empathetic state" which, when presented to the learning agent, produces behaviours that mimic the other agent. Our approach is applicable to multi-agent scenarios consisting of a single learning agent and other (independent) agents acting according to fixed policies. This architecture is particularly beneficial for (but not limited to) algorithms using a composite value or reward function. We show our method produces better performance in multi-agent games, where it robustly estimates the other's model in different environment configurations. Additionally, we show that the empathetic states are human interpretable, and thus verifiable.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes