A General Framework for Interacting Bayes-Optimally with Self-Interested Agents using Arbitrary Parametric Model and Model Prior
This work addresses a practical limitation in multi-agent reinforcement learning for scenarios involving self-interested agents, though it is incremental as it builds on existing Bayesian frameworks.
The paper tackles the problem of Bayes-optimal interaction with self-interested agents in multi-agent environments by generalizing Bayesian reinforcement learning to use arbitrary parametric models and priors, overcoming limitations of the Flat-Dirichlet-Multinomial prior. Empirical results show it outperforms existing multi-agent reinforcement learning algorithms.
Recent advances in Bayesian reinforcement learning (BRL) have shown that Bayes-optimality is theoretically achievable by modeling the environment's latent dynamics using Flat-Dirichlet-Multinomial (FDM) prior. In self-interested multi-agent environments, the transition dynamics are mainly controlled by the other agent's stochastic behavior for which FDM's independence and modeling assumptions do not hold. As a result, FDM does not allow the other agent's behavior to be generalized across different states nor specified using prior domain knowledge. To overcome these practical limitations of FDM, we propose a generalization of BRL to integrate the general class of parametric models and model priors, thus allowing practitioners' domain knowledge to be exploited to produce a fine-grained and compact representation of the other agent's behavior. Empirical evaluation shows that our approach outperforms existing multi-agent reinforcement learning algorithms.