Transfer learning for reinforcement learning domains: a survey

zbMATH Open1235.68196MaRDI QIDQ2880944FDOQ2880944

Peter Stone, Matthew E. Taylor

Publication date: 17 April 2012

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: http://www.jmlr.org/papers/v10/taylor09a.html

Recommendations

• A survey on transfer learning for multiagent reinforcement learning systems
• Transfer learning via inter-task mappings for temporal difference learning
• Transfer in reinforcement learning via shared features
• Transfer in variable-reward hierarchical reinforcement learning

zbMATH Keywords

multi-task learningtransfer learningreinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cited In (49)

• Visual transfer for reinforcement learning via gradient penalty based Wasserstein domain confusion
• Progressive learning: a deep learning framework for continual learning
• Rule extraction for transfer learning
• POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
• Task-specific loss: a teacher-centered approach to transfer learning between distinctly structured robotic agents
• Embedding active learning in batch-to-batch optimization using reinforcement learning
• Title not available (Why is that?)
• A Hybrid Transfer Algorithm for Reinforcement Learning Based on Spectral Method
• Transfer of experience between reinforcement learning environments with progressive difficulty
• Robust optimal well control using an adaptive multigrid reinforcement learning framework
• Modeling of autonomous problem solving process by dynamic construction of task models in multiple tasks environment
• Transfer in variable-reward hierarchical reinforcement learning
• Abstraction in data-sparse task transfer
• A Gentle Introduction to Reinforcement Learning
• A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics
• A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
• Reinforcement learning
• Action-model acquisition for planning via transfer learning
• Title not available (Why is that?)
• Title not available (Why is that?)
• Exact learning dynamics of deep linear networks with prior knowledge
• A transfer forecasting model for container throughput guided by discrete PSO
• A Bayesian approach to (online) transfer learning: theory and algorithms
• Quantum classifiers for domain adaptation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Improving the efficiency of reinforcement learning for a spacecraft powered descent with Q-learning
• Transferring knowledge as heuristics in reinforcement learning: a case-based approach
• Optimal design of priors constrained by external predictors
• Phase portraits as movement primitives for fast humanoid robot control
• A taxonomy for similarity metrics between Markov decision processes
• Making friends on the fly: cooperating with new teammates
• Reward is enough
• Model-based Reinforcement Learning: A Survey
• Transferable dynamics models for efficient object-oriented reinforcement learning
• Bayesian policy reuse
• Overlapping layered learning
• Preference-based reinforcement learning: a formal framework and a policy iteration algorithm
• Scalable transfer learning in heterogeneous, dynamic environments
• Fast rates by transferring from auxiliary hypotheses
• Integration of memory systems supporting non-symbolic representations in an architecture for lifelong development of artificial agents
• Permutation flow shop scheduling with multiple lines and demand plans using reinforcement learning
• Realizing self-adaptive systems via online reinforcement learning and feature-model-guided exploration
• Exact learning dynamics of deep linear networks with prior knowledge
• Multi-fidelity reinforcement learning framework for shape optimization
• Analysis on methods to effectively improve transfer learning performance
• Inverse Kalman filtering problems for discrete-time systems
• Hierarchical clustering optimizes the tradeoff between compositionality and expressivity of task structures for flexible reinforcement learning
• Reinforcement learning: an industrial perspective

This page was built for publication: Transfer learning for reinforcement learning domains: a survey

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2880944)