Exploration and Incentives in Reinforcement Learning
This addresses the challenge of mechanism design in stateful RL for multi-agent systems, representing a novel extension from stateless to stateful environments.
The paper tackles the problem of incentivizing self-interested agents to explore in reinforcement learning when they prefer to exploit, by designing an algorithm that explores all reachable states in an MDP with provable guarantees similar to prior stateless settings.
How do you incentivize self-interested agents to $\textit{explore}$ when they prefer to $\textit{exploit}$? We consider complex exploration problems, where each agent faces the same (but unknown) MDP. In contrast with traditional formulations of reinforcement learning, agents control the choice of policies, whereas an algorithm can only issue recommendations. However, the algorithm controls the flow of information, and can incentivize the agents to explore via information asymmetry. We design an algorithm which explores all reachable states in the MDP. We achieve provable guarantees similar to those for incentivizing exploration in static, stateless exploration problems studied previously. To the best of our knowledge, this is the first work to consider mechanism design in a stateful, reinforcement learning setting.