Abstract
We consider the problem of imitation learning where the examples, demonstrated by an expert, cover only a small part of a large state space. Inverse Reinforcement Learning (IRL) provides an efficient tool for generalizing the demonstration, based on the assumption that the expert is optimally acting in a Markov Decision Process (MDP). Most of the past work on IRL requires that a (near)- optimal policy can be computed for different reward functions. However, this requirement can hardly be satisfied in systems with a large, or continuous, state space. In this paper, we propose a model-free IRL algorithm, where the relative entropy between the empirical distribution of the state-action trajectories under a baseline policy and their distribution under the learned policy is minimized by stochastic gradient descent. We compare this new approach to well-known IRL algorithms using learned MDP models. Empirical results on simulated car racing, gridworld and ball-in-a-cup problems show that our approach is able to learn good policies from a small number of demonstrations.
| Original language | American English |
|---|---|
| Pages (from-to) | 182-189 |
| Number of pages | 8 |
| Journal | Journal of Machine Learning Research |
| Volume | 15 |
| State | Published - 2011 |
| Externally published | Yes |
| Event | 14th International Conference on Artificial Intelligence and Statistics, AISTATS 2011 - Fort Lauderdale, FL, United States Duration: Apr 11 2011 → Apr 13 2011 |
ASJC Scopus subject areas
- Software
- Control and Systems Engineering
- Statistics and Probability
- Artificial Intelligence