Inverse reinforcement learning in partially observable environments

MaRDI QIDQ5396624zbMATH OpenFDO

Authors Jaedeug Choi, Kee-Eung Kim

Publication date 3 February 2014

Full work available at URL http://www.jmlr.org/papers/v12/choi11a.html

zbMATH Keywords

inverse optimizationinverse reinforcement learninglinear programmingpartially observable Markov decision processquadratically constrained programming

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Linear programming (90C05) Markov and semi-Markov decision processes (90C40)

Recommendations

• Analysis of Inverse Reinforcement Learning with Perturbed Demonstrations
• Inverse reinforcement learning from summary data
• A survey of inverse reinforcement learning: challenges, methods and progress
• Multi-robot inverse reinforcement learning under occlusion with estimation of state transitions
• Modular inverse reinforcement learning for visuomotor behavior

Cited in

(27)

• Inverse reinforcement learning from summary data
• Multi-robot inverse reinforcement learning under occlusion with estimation of state transitions
• Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs
• Partially observable environment estimation with uplift inference for reinforcement learning based recommendation
• Inverse reinforcement learning for multi-player noncooperative apprentice games
• A survey of inverse reinforcement learning: challenges, methods and progress
• Inverse optimization for assessing emerging technologies in breast cancer screening
• Multi-task reinforcement learning in partially observable stochastic environments
• Analysis of Inverse Reinforcement Learning with Perturbed Demonstrations
• scientific article; zbMATH DE number 5547961 (Why is no real title available?)
• Modular inverse reinforcement learning for visuomotor behavior
• ISO Learning Approximates a Solution to the Inverse-Controller Problem in an Unsupervised Behavioral Paradigm
• Inverse reinforcement learning via nonparametric spatio-temporal subgoal modeling
• Bayesian learning of noisy Markov decision processes
• Infinite Time Horizon Maximum Causal Entropy Inverse Reinforcement Learning
• Langevin dynamics for adaptive inverse reinforcement learning of stochastic gradient algorithms
• Theory and Applications of Models of Computation
• Online inverse reinforcement learning for nonlinear systems with adversarial attacks
• Learning reward machines: a study in partially observable reinforcement learning
• Model-free inverse reinforcement learning with multi-intention, unlabeled, and overlapping demonstrations
• Inverse reinforcement learning through logic constraint inference
• Correction to: ``Model-free inverse reinforcement learning with multi-intention, unlabeled, and overlapping demonstrations
• Task-guided IRL in POMDPs that scales
• Trajectory modeling via random utility inverse reinforcement learning
• Joint learning of reward machines and policies in environments with partially known semantics
• Reinforcement learning
• Nonuniqueness and convergence to equivalent solutions in observer-based inverse reinforcement learning

This page was built for publication: Inverse reinforcement learning in partially observable environments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5396624)