Results 91 to 100 of about 311 (117)
Some of the next articles are maybe not open access.
Trust-Region Inverse Reinforcement Learning
IEEE Transactions on Automatic ControlThis paper proposes a new unified inverse reinforcement learning (IRL) framework based on trust-region methods and a recently proposed Pontryagin differential programming (PDP) method in Jin et al. (2020), which aims to learn the parameters in both the system model and the cost function for three types of problems, namely, N-player nonzero-sum ...
Kun Cao 0002, Lihua Xie 0001
openaire +2 more sources
Maximum Entropy Inverse Reinforcement Learning
2018Recent research has shown the beneļ¬t of framing problems of imitation learning as solutions to Markov Decision Problems. This approach reduces learning to the problem of re- covering a utility function that makes the behavior induced by a near-optimal policy closely mimic demonstrated behavior. In this work, we develop a probabilistic approach based
Brian D. Ziebart +3 more
openaire +2 more sources
Batch-Constraint Inverse Reinforcement Learning
2021We consider a completely offline inverse reinforcement learning setup, i.e., where the reward function is unknown and the interaction with the environment is not possible. This typically occurs in situations where data collection is risky or costly, such as healthcare or industrial controls.
Mao Chen 0005 +4 more
openaire +1 more source
Inverse reinforcement learning for interactive systems
Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication, 2013Human machine interaction is a field where machine learning is present at almost any level, from human activity recognition to natural language generation. The interaction manager is probably one of the latest components of an interactive system that benefited from machine learning techniques.
openaire +1 more source
Hierarchical Adversarial Inverse Reinforcement Learning
IEEE Transactions on Neural Networks and Learning SystemsImitation learning (IL) has been proposed to recover the expert policy from demonstrations. However, it would be difficult to learn a single monolithic policy for highly complex long-horizon tasks of which the expert policy usually contains subtask hierarchies.
Jiayu Chen 0006 +2 more
openaire +2 more sources
Inverse Reinforcement Learning in Tracking Control Based on Inverse Optimal Control
IEEE Transactions on Cybernetics, 2022Jialu Fan, Bosen Lian, Wenqian Xue
exaly
Sophisticated Swarm Reinforcement Learning by Incorporating Inverse Reinforcement Learning
2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2023Yasuaki Kuroe, Kenya Takeuchi
openaire +1 more source
Online inverse reinforcement learning for nonlinear systems with adversarial attacks
International Journal of Robust and Nonlinear Control, 2021Bosen Lian
exaly
From inverse optimal control to inverse reinforcement learning: A historical review
Annual Reviews in Control, 2020Aref Shahmansoorian +2 more
exaly
Inverse reinforcement learning for multi-player noncooperative apprentice games
Automatica, 2022Bosen Lian, Wenqian Xue, Tianyou Chai
exaly