Parameterized modular inverse reinforcement learning
MetadataShow full item record
Reinforcement learning and inverse reinforcement learning can be used to model and understand human behaviors. However, due to the curse of dimensionality, their use as a model for human behavior has been limited. Inspired by observed natural behaviors, one approach is to decompose complex tasks into independent sub-tasks, or modules. Using this approach, we extended earlier work on modular inverse reinforcement learning, and developed what we called a parameterized modular inverse reinforcement learning algorithm. We first demonstrate the correctness and efficiency of our algorithm in a simulated navigation task. We then show that our algorithm is able to estimate a reward function and discount factor for real human navigation behaviors in a virtual environment, and train an agent that imitates the behavior of human subjects.
Showing items related by title, author, creator and subject.
Zhang, Ruohan (2014-08)Modular reinforcement learning is an approach to resolve the curse of dimensionality problem in traditional reinforcement learning. We design and implement a modular reinforcement learning algorithm, which is based on three ...
Whiteson, Shimon Azariah (2007-05)In reinforcement learning, an autonomous agent seeks an effective control policy for tackling a sequential decision task. Unlike in supervised learning, the agent never sees examples of correct or incorrect behavior but ...
Taylor, Matthew Edmund (2008-08)Reinforcement learning (RL) methods have become popular in recent years because of their ability to solve complex tasks with minimal feedback. While these methods have had experimental successes and have been shown to ...