Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics
This addresses a limitation in IRL for scenarios where assumptions about accessible dynamics samples are not met, though it appears incremental as it builds on existing IRL methods.
The paper tackles the problem of inverse reinforcement learning (IRL) when the system dynamics are unknown and additional samples are not available, by proposing a gradient-based approach that simultaneously estimates rewards and dynamics. The evaluation shows improvements in sample efficiency and accuracy for estimated reward functions and transition models.
Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies depend on both the stochastic system dynamics as well as the reward function, the solution of the inverse problem is significantly influenced by both. Current IRL approaches assume that if the transition model is unknown, additional samples from the system's dynamics are accessible, or the observed behavior provides enough samples of the system's dynamics to solve the inverse problem accurately. These assumptions are often not satisfied. To overcome this, we present a gradient-based IRL approach that simultaneously estimates the system's dynamics. By solving the combined optimization problem, our approach takes into account the bias of the demonstrations, which stems from the generating policy. The evaluation on a synthetic MDP and a transfer learning task shows improvements regarding the sample efficiency as well as the accuracy of the estimated reward functions and transition models.