Interactive Inverse Reinforcement Learning for Cooperative Games
This addresses the challenge of enabling effective cooperation in multi-agent systems where reward functions are unknown, which is incremental as it builds on existing interactive learning frameworks.
The paper tackles the problem of designing autonomous agents that learn to cooperate with a suboptimal partner without access to the joint reward function, modeled as a cooperative episodic two-agent Markov decision process, and shows that the reward function can be learned efficiently when the learning agent's policies significantly affect the transition function.
We study the problem of designing autonomous agents that can learn to cooperate effectively with a potentially suboptimal partner while having no access to the joint reward function. This problem is modeled as a cooperative episodic two-agent Markov decision process. We assume control over only the first of the two agents in a Stackelberg formulation of the game, where the second agent is acting so as to maximise expected utility given the first agent's policy. How should the first agent act in order to learn the joint reward function as quickly as possible and so that the joint policy is as close to optimal as possible? We analyse how knowledge about the reward function can be gained in this interactive two-agent scenario. We show that when the learning agent's policies have a significant effect on the transition function, the reward function can be learned efficiently.