Value Functions for RL-Based Behavior Transfer: A Comparative Study

87 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.

Transfer in variable-reward hierarchical reinforcement learning (2008, background): “Taylor et al. (2005) propose a value-function mapping approach for transfer between source and target reinforcement learning tasks.”
Probabilistic policy reuse in a reinforcement learning agent (2006, background): “Transfer learning in more complex domains, as the Keepaway task in robot soccer, requires a mapping between tasks that use different state and action spaces [15, 14].”
Value-Function-Based Transfer for Reinforcement Learning Using Structure Mapping (2006, methodology): “The value-function-based transfer method (Taylor, Stone, & Liu, 2005) can deal with the general case˚S = S and/orÅ = A by using a transfer functional ρ that maps the q-function of the source problem , ˚ q, to a q-function of the target problem, q = ρ(˚ q), provided that the rewards in both problems…”
Proto-transfer Learning in Markov Decision Processes Using Spectral Methods (2006, background): “Previous work has accelerated learning when transferring behaviors between tasks and domains (Taylor et al., 2005), but we transfer representation and reuse knowledge to learn comparably on a new task or domain.”
Transfer Learning via Inter-Task Mappings for Temporal Difference Learning (2007, background): “This article contains and extends material published in two conference papers (Taylor and Stone, 2005; Taylor et al., 2005).”