Off-policy reinforcement learning with Gaussian processes

Off-policy reinforcement learning with Gaussian processes

An off-policy Bayesian nonparameteric approximate reinforcement learning framework, termed as GPQ, that employs a Gaussian processes (GP) model of the value (Q) function is presented in both the batch and online settings. Sufficient conditions on GP hyperparameter selection are established to guaran...

Full description

Bibliographic Details
Main Authors:	Chowdhary, Girish (Author), Liu, Miao (Author), Grande, Robert (Contributor), Walsh, Thomas (Contributor), How, Jonathan P. (Contributor), Carin, Lawrence (Author)
Other Authors:	Massachusetts Institute of Technology. Aerospace Controls Laboratory (Contributor), Massachusetts Institute of Technology. Department of Aeronautics and Astronautics (Contributor)
Format:	Article
Language:	English
Published:	Institute of Electrical and Electronics Engineers (IEEE), 2015-05-11T19:13:37Z.
Subjects:	Article
Online Access:	Get fulltext

Similar Items

Bayesian Nonparametric Adaptive Control Using Gaussian Processes
by: Chowdhary, Girish, et al.
Published: (2015)

Stick-breaking policy learning in Dec-POMDPs
by: Amato, Christopher, et al.
Published: (2016)

Efficient Reinforcement Learning using Gaussian Processes
Published: (2010)

Off-Policy Reinforcement Learning for Robotics
by: Tosatto, Samuele
Published: (2021)

Gaussian processes non‐linear inverse reinforcement learning
by: Qifeng Qiao, et al.
Published: (2021-06-01)

Gaussian Process Models for Robust Regression, Classification, and Reinforcement Learning
by: Kuß, Malte
Published: (2006)

Reinforcement Learning with Gaussian Processes for Unmanned Aerial Vehicle Navigation
by: Gondhalekar, Nahush Ramesh
Published: (2017)

Reinforcement learning with multi-fidelity simulators
by: Cutler, Mark Johnson, et al.
Published: (2016)

Gaussian Processes in Reinforcement Learning: Stability Analysis and Efficient Value Propagation
by: Vinogradska, Julia
Published: (2018)

Multimodal Control in Uncertain Environments using Reinforcement Learning and Gaussian Processes
by: Mariano De Paula, et al.
Published: (2015-10-01)

Computationally efficient Gaussian Process changepoint detection and regression
by: Grande, Robert Conlin
Published: (2014)

Enhanced Off-Policy Reinforcement Learning With Focused Experience Replay
by: Seung-Hyun Kong, et al.
Published: (2021-01-01)

Experiments in off-policy reinforcement learning with the GQ(lambda) algorithm
by: Delp, Michael
Published: (2011)

Terrain Aided Navigation for Autonomous Underwater Vehicles with Local Gaussian Processes
by: Chowdhary, Abhilash
Published: (2017)

Policy Distillation and Value Matching in Multiagent Reinforcement Learning
by: Wadhwania, Samir, et al.
Published: (2021)

Continuous reinforcement learning with incremental Gaussian mixture models
by: Pinto, Rafael Coimbra
Published: (2017)

Continuous reinforcement learning with incremental Gaussian mixture models
by: Pinto, Rafael Coimbra
Published: (2017)

Continuous reinforcement learning with incremental Gaussian mixture models
by: Pinto, Rafael Coimbra
Published: (2017)

Approximate Dynamic Programming Using Bellman Residual Elimination and Gaussian Process Regression
by: Bethke, Brett M., et al.
Published: (2010)

Approximate Dynamic Programming Using Bellman Residual Elimination and Gaussian Process Regression
by: How, Jonathan P., et al.
Published: (2010)

Exploration with Multiple Random ε-Buffers in Off-Policy Deep Reinforcement Learning
by: Chayoung Kim, et al.
Published: (2019-11-01)

Optimal Control of Iron-Removal Systems Based on Off-Policy Reinforcement Learning
by: Ning Chen, et al.
Published: (2020-01-01)

Gaussian Processes for Machine Learning
Published: (2005)

Region-of-convergence estimation for learning-based adaptive controllers
by: Topcu, Ufuk, et al.
Published: (2018)

Socially aware motion planning with deep reinforcement learning
by: Chen, Yu Fan, et al.
Published: (2018)

Rapid transfer of controllers between UAVs using learning-based adaptive control
by: Chowdhary, Girish, et al.
Published: (2015)

Dynamic clustering via asymptotics of the dependent Dirichlet process mixture
by: Campbell, Trevor David, et al.
Published: (2015)

Adaptive Planning for Markov Decision Processes with Uncertain Transition Models via Incremental Feature Dependency Discovery
by: Geramifard, Alborz, et al.
Published: (2013)

Learning to Teach in Cooperative Multiagent Reinforcement Learning
by: Omidshafie, Shayegan, et al.
Published: (2021)

Bayesian Nonparametric Inverse Reinforcement Learning
by: How, Jonathan P., et al.
Published: (2013)

Sensor Selection in High-Dimensional Gaussian Trees with Nuisances
by: Levine, Daniel, et al.
Published: (2015)

Value-of-information aware active task assignment
by: Mu, Beipeng, et al.
Published: (2013)

Efficient distributed sensing using adaptive censoring-based inference
by: Mu, Beipeng, et al.
Published: (2017)

Concurrent learning for convergence in adaptive control without persistency of excitation
by: Chowdhary, Girish
Published: (2011)

Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning
by: Chen, Yu Fan, et al.
Published: (2018)

Detecting periodicities with Gaussian processes
by: Nicolas Durrande, et al.
Published: (2016-04-01)

Deep decentralized multi-task multi-agent reinforcement learning under partial observability
by: How, Jonathan
Published: (2021)

Improving the efficiency of Bayesian inverse reinforcement learning
by: How, Jonathan P., et al.
Published: (2013)

Learning safe predictive control with gaussian processes
by: Van Niekerk, Benjamin
Published: (2020)

Data-Driven Nonzero-Sum Game for Discrete-Time Systems Using Off-Policy Reinforcement Learning
by: Yongliang Yang, et al.
Published: (2020-01-01)