OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
This work addresses the challenge of inverse reinforcement learning in complex tasks with diverse reward functions, offering an incremental improvement by extending the options framework.
The paper tackles the problem of learning from expert demonstrations with diverse underlying reward functions by proposing OptionGAN, a method that simultaneously recovers reward and policy options using generative adversarial inverse reinforcement learning. The result shows significant performance increases in one-shot transfer learning on continuous control tasks.
Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectories arising from a diverse set of underlying reward functions rather than a single one. Thus, in inverse reinforcement learning, it is useful to consider such a decomposition. The options framework in reinforcement learning is specifically designed to decompose policies in a similar light. We therefore extend the options framework and propose a method to simultaneously recover reward options in addition to policy options. We leverage adversarial methods to learn joint reward-policy options using only observed expert states. We show that this approach works well in both simple and complex continuous control tasks and shows significant performance increases in one-shot transfer learning.