Nonparametric Bayesian reward segmentation for skill discovery using inverse reinforcement learning.
Pravesh RanchodBenjamin RosmanGeorge Dimitri KonidarisPublished in: IROS (2015)
Keyphrases
- inverse reinforcement learning
- nonparametric bayesian
- partially observable environments
- reward function
- preference elicitation
- level set
- image segmentation
- mixture modeling
- statistical modeling
- data mining
- temporal difference
- energy function
- dirichlet process
- reinforcement learning
- monte carlo
- markov chain
- probabilistic model