Timezone: »
We present a probabilistic algorithm for nonlinear inverse reinforcement learning. The goal of inverse reinforcement learning is to learn the reward function in a Markov decision process from expert demonstrations. While most prior inverse reinforcement learning algorithms represent the reward as a linear combination of a set of features, we use Gaussian processes to learn the reward as a nonlinear function, while also determining the relevance of each feature to the expert's policy. Our probabilistic algorithm allows complex behaviors to be captured from suboptimal stochastic demonstrations, while automatically balancing the simplicity of the learned reward structure against its consistency with the observed actions.
Author Information
Sergey Levine (Stanford University)
Zoran Popovic (University of Washington)
Vladlen Koltun (Adobe Research)
More from the Same Authors
-
2016 Poster: Backprop KF: Learning Discriminative Deterministic State Estimators »
Tuomas Haarnoja · Anurag Ajay · Sergey Levine · Pieter Abbeel -
2016 Poster: Guided Policy Search via Approximate Mirror Descent »
William H Montgomery · Sergey Levine -
2016 Poster: Learning to Poke by Poking: Experiential Learning of Intuitive Physics »
Pulkit Agrawal · Ashvin Nair · Pieter Abbeel · Jitendra Malik · Sergey Levine -
2016 Oral: Learning to Poke by Poking: Experiential Learning of Intuitive Physics »
Pulkit Agrawal · Ashvin Nair · Pieter Abbeel · Jitendra Malik · Sergey Levine -
2016 Poster: Unsupervised Learning for Physical Interaction through Video Prediction »
Chelsea Finn · Ian Goodfellow · Sergey Levine -
2011 Poster: Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials »
Philipp Krähenbühl · Vladlen Koltun -
2011 Oral: Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials »
Philipp Krähenbühl · Vladlen Koltun -
2010 Poster: Feature Construction for Inverse Reinforcement Learning »
Sergey Levine · Zoran Popovic · Vladlen Koltun