Transfer via inter-task mappings in policy search reinforcement learning

By Matthew E. Taylor, Shimon Whiteson, Peter Stone. 2007

147 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Transfer Learning for Reinforcement Learning Domains: A Survey (2009, background): “While choosing a range of thresholds to compare over may produce more representative measures (cf., Taylor et al., 2007b), this leads to having to generating a time vs. threshold curve rather than producing a single real valued number that evaluates a transfer algorithm’s efficacy.”
Policy Transfer using Reward Shaping (2015, background): “the use of an old policy to speed up learning in a new task, without any reference to a low level algorithm-specific representation of that policy [6, 22].”
Autonomous Agents and Multi-agent Systems Manuscript No. Learning Potential Functions and Their Representations for Multi-task Reinforcement Learning (unknown): “[78] learn rules that summarize a learned source task policy and incorporate these as an extra action in the target task, to be learned by a policy-search method.”
Reinforcement Learning Transfer Using a Sparse Coded Inter-task Mapping (2011, background): “For example, semantic knowledge about state features between two tasks may be used [8, 5], background knowledge about the range or type of state variables can be used [13, 17], or transition models for each possible mapping could be generated and tested [14].”
Autonomous transfer for reinforcement learning (2008, background): “[20] M. E. Taylor, P. Stone, and Y. Liu.”
Automatically Mapped Transfer between Reinforcement Learning Tasks via Three-Way Restricted Boltzmann Machines (2013, background): “For example, semantic knowledge about state features between two tasks may be used [8,10], background knowledge about the range or type of state variables can be used [14,19], or transition models for each possible mapping could be generated and tested [16].”
Unsupervised Cross-Domain Transfer in Policy Gradient Reinforcement Learning via Manifold Alignment (2015, background): “All rights reserved. when the source and target tasks have different state and/or action spaces, an inter-task mapping (Taylor et al. 2007a) that describes the relationship between the two tasks is typically needed.”
Mapping and Revising Markov Logic Networks for Transfer Learning (2007, background): “It has been studied for a variety of problems, including text classification (Raina, Ng, & Koller 2006) and reinforcement learning (Torrey et al. 2005; Taylor, Whiteson, & Stone 2007 ).”