Results 61 to 70 of about 88,537 (171)

Scalable Bayesian Inverse Reinforcement Learning

, 2021
Bayesian inference over the reward presents an ideal solution to the ill-posed nature of the inverse reinforcement learning problem. Unfortunately current methods generally do not scale well beyond the small tabular setting due to the need for an inner-loop MDP solver, and even non-Bayesian methods that do themselves scale often require extensive ...
Chan, Alex J., van der Schaar, Mihaela
openaire   +2 more sources

Contingency-based flexibility mechanisms through a reinforcement learning model in adults with attention-deficit/hyperactivity disorder and obsessive-compulsive disorder

Comprehensive Psychiatry
Background and aims: Impaired cognitive flexibility is associated with the characteristic symptomatology of ADHD and OCD. However, the mechanisms underlying learning and flexibility under uncertainty in adults with OCD or ADHD remain unclear.
Rocío Rodríguez-Herrera, José Juan León, Pilar Fernández-Martín, Ana Sánchez-Kuhn, Miguel Soto-Ontoso, Laura Amaya-Pascasio, Patricia Martínez-Sánchez, Pilar Flores   +7 more
doaj   +1 more source

Context-Hierarchy Inverse Reinforcement Learning

, 2022
An inverse reinforcement learning (IRL) agent learns to act intelligently by observing expert demonstrations and learning the expert's underlying reward function. Although learning the reward functions from demonstrations has achieved great success in various tasks, several other challenges are mostly ignored. Firstly, existing IRL methods try to learn
Gao, Wei, Hsu, David, Lee, Wee Sun
openaire   +2 more sources

Deep reinforcement learning for inverse inorganic materials design

npj Computational Materials
A major obstacle to the realization of novel inorganic materials with desirable properties is efficient materials discovery over both the materials property and synthesis spaces.
Christopher Karpovich, Elton Pan, Elsa A. Olivetti   +2 more
doaj   +1 more source

Thinking as human: Self-reflective reinforcement learning framework for fertilization decision-making

Smart Agricultural Technology
Variable-rate fertilization based on reinforcement learning has achieved significant success in simulated environments. However, issues of insecurity and inefficiency led by blind exploration mechanism constitute impediments to apply reinforcement ...
Shulang Li, Jie Liu, Yang Yang, Rujia Shen, Jingchi Jiang   +4 more
doaj   +1 more source

Optimizing Reinforcement Learning with Limited HRI Demonstrations: A Task-Oriented Weight Update Method with Analysis of Multi-head and Layer Feature Combinations

International Journal of Computational Intelligence Systems
To address the challenge of training reinforcement learning (RL) networks with limited data in Human-Robot Interaction (HRI), we introduce a novel task-oriented update method that combines meta-inverse reinforcement learning (Meta-IRL) and transformer ...
Qinghua Chen, Jessica Korneder, Osamah A. Rawashdeh, Yanfeng Wang, Wing-Yue Geoffrey Louie   +4 more
doaj   +1 more source

Inverse Delayed Reinforcement Learning

Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed disturbances. Instead of relying on direct observations, our approach employs an efficient off-policy adversarial training ...
Zhan, Simon Sinong, Wu, Qingyuan, Ruan, Zhian, Yang, Frank, Wang, Philip, Wang, Yixuan, Jiao, Ruochen, Huang, Chao, Zhu, Qi   +8 more
openaire   +2 more sources

Distributional Inverse Reinforcement Learning

We propose a distributional framework for offline Inverse Reinforcement Learning (IRL) that jointly models uncertainty over reward functions and full distributions of returns. Unlike conventional IRL approaches that recover a deterministic reward estimate or match only expected returns, our method captures richer structure in expert behavior ...
Wu, Feiyang, Zhao, Ye, Wu, Anqi
openaire   +2 more sources

Inverse Risk-Sensitive Reinforcement Learning

IEEE Transactions on Automatic Control, 2020
We address the problem of inverse reinforcement learning in Markov decision processes where the agent is risk-sensitive. In particular, we model risk-sensitivity in a reinforcement learning framework by making use of models of human decision-making having their origins in behavioral psychology, behavioral economics, and neuroscience.
Lillian J. Ratliff, Eric Mazumdar
openaire   +3 more sources

Stable Inverse Reinforcement Learning: Policies From Control Lyapunov Landscapes

IEEE Open Journal of Control Systems
Learning from expert demonstrations to flexibly program an autonomous system with complex behaviors or to predict an agent's behavior is a powerful tool, especially in collaborative control settings.
SAMUEL TESFAZGI, Leonhard Sprandl, Armin Lederer, Sandra Hirche   +3 more
doaj   +1 more source