AILGMAMLOct 1, 2018

Interactive Agent Modeling by Learning to Probe

arXiv:1810.00510v14 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of agent modeling for AI systems in interactive environments, offering a novel approach that goes beyond passive observation, though it is incremental in building on curiosity-driven methods.

The paper tackles the problem of modeling other agents' intentions and skills by introducing an interactive probing scheme, where a learner actively probes a target agent to observe richer behaviors, resulting in better generalization to novel scenarios and improved performance in applications like planning, collaboration, and competition.

The ability of modeling the other agents, such as understanding their intentions and skills, is essential to an agent's interactions with other agents. Conventional agent modeling relies on passive observation from demonstrations. In this work, we propose an interactive agent modeling scheme enabled by encouraging an agent to learn to probe. In particular, the probing agent (i.e. a learner) learns to interact with the environment and with a target agent (i.e., a demonstrator) to maximize the change in the observed behaviors of that agent. Through probing, rich behaviors can be observed and are used for enhancing the agent modeling to learn a more accurate mind model of the target agent. Our framework consists of two learning processes: i) imitation learning for an approximated agent model and ii) pure curiosity-driven reinforcement learning for an efficient probing policy to discover new behaviors that otherwise can not be observed. We have validated our approach in four different tasks. The experimental results suggest that the agent model learned by our approach i) generalizes better in novel scenarios than the ones learned by passive observation, random probing, and other curiosity-driven approaches do, and ii) can be used for enhancing performance in multiple applications including distilling optimal planning to a policy net, collaboration, and competition. A video demo is available at https://www.dropbox.com/s/8mz6rd3349tso67/Probing_Demo.mov?dl=0

Foundations

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

Your Notes