Bayesian Nonparametric Inverse Reinforcement Learning
Inverse reinforcement learning (IRL) is the task of learning the reward function of a Markov Decision Process (MDP) given the transition function and a set of observed demonstrations in the form of state-action pairs. Current IRL algorithms attempt to find a single reward function which explains the...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer-Verlag,
2013-10-23T16:12:50Z.
|
| Subjects: | |
| Online Access: | Get fulltext |