Results 11 to 20 of about 311 (117)
Inverse Reinforcement Learning without Reinforcement Learning
CoRR, 2023 Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunately, traditional IRL methods suffer from a computational weakness: they require repeatedly solving a hard reinforcement learning (RL) problem as a subroutine. This is counter-
Gokul Swamy 0001 +3 more
openaire +2 more sources
Inverse reinforcement learning in contextual MDPs [PDF]
Machine Learning, 2021 AbstractWe consider the task of Inverse Reinforcement Learning in Contextual Markov Decision Processes (MDPs). In this setting, contexts, which define the reward and transition kernel, are sampled from a distribution. In addition, although the reward is a function of the context, it is not provided to the agent.
Stav Belogolovsky +4 more
openaire +2 more sources
Misspecification in Inverse Reinforcement Learning
Proceedings of the AAAI Conference on Artificial Intelligence, 2023 The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function R from a policy pi. To do this, we need a model of how pi relates to R. In the current literature, the most common models are optimality, Boltzmann rationality, and causal entropy maximisation. One of the primary motivations behind IRL is to infer human preferences from human
Joar Skalse, Alessandro Abate
openaire +2 more sources
Offline Inverse Reinforcement Learning
CoRR, 2021 The objective of offline RL is to learn optimal policies when a fixed exploratory demonstrations data-set is available and sampling additional observations is impossible (typically if this operation is either costly or rises ethical questions). In order to solve this problem, off the shelf approaches require a properly defined cost function (or its ...
Firas Jarboui, Vianney Perchet
openaire +2 more sources
Lifelong Inverse Reinforcement Learning
CoRR, 2022 Published in NeurIPS 2018.
Jorge A. Mendez +2 more
openaire +3 more sources
Identifiability in inverse reinforcement learning
CoRR, 2021 Inverse reinforcement learning attempts to reconstruct the reward function in a Markov decision problem, using observations of agent actions. As already observed in Russell [1998] the problem is ill-posed, and the reward function is not identifiable, even under the presence of perfect information about optimal behavior.
Cao, H, Cohen, S, Szpruch, L
openaire +4 more sources
Inverse Reinforcement Learning for Strategy Identification [PDF]
2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2021 The paper has been accepted as a regular paper in IEEE International Conference on Systems, Man, and Cybernetics (SMC ...
Mark Rucker +3 more
openaire +2 more sources
Quantum generative adversarial imitation learning
New Journal of Physics, 2023 Investigating quantum advantage in the NISQ era is a challenging problem whereas quantum machine learning becomes the most promising application that can be resorted to.
Tailong Xiao +4 more
doaj +1 more source
Repeated Inverse Reinforcement Learning
CoRR, 2017 The first two authors contributed equally to this work.
Kareem Amin 0002 +2 more
openaire +3 more sources
Regularized Inverse Reinforcement Learning
CoRR, 2020 26 pages, 7 ...
Wonseok Jeon +5 more
openaire +3 more sources