Proto-transfer Learning in Markov Decision Processes Using Spectral Methods

By Kimberly Ferguson, Sridhar Mahadevan. 2006

60 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.

Citations in the corpus

Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations (2015, methodology): “from previous tasks to reduce training time [11, 12], similar to shaping [49].”
Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes (2007, background): “We have recently begun to investigate a framework called proto-transfer learning to explore the transfer of learned representations from one task to another (in contrast to transferring learned policies) (Ferguson and Mahadevan, 2006).”
Construction of approximation spaces for reinforcement learning (2013, methodology): “(2007) and Mahadevan and Maggioni (2007), this point of view puts emphasis on the reuse of prior experience, as investigated in transfer learning (Taylor and Stone, 2009; Ferguson and Mahadevan, 2006; Ferrante et al., 2008).”
Transfer Learning for Reinforcement Learning Domains: A Survey (2009, background): “For instance, when transferring between maze tasks, b sis functions could be learned (Ferguson and Mahadevan, 2006) in the source task, a set of actions to transfer could be selected after training on a set of additional generated source tasks (Sher tov and Stone, 2005), and then parts of different…”
Transfer in Reinforcement Learning: A Framework and a Survey (2012, methodology): “Ferguson and Mahadevan (2006) generalize this approach to problems with slightly different dynamics.”
Transfer in Reinforcement Learning via Shared Features (2012, background): “Representation transfer has so far focused primarily on task sequences where reward function or dynamics differ but the state space remains the same (Ferguson and Mahadevan, 2006; Ferrante et al., 2008).”
Autonomous Agents and Multi-agent Systems Manuscript No. Learning Potential Functions and Their Representations for Multi-task Reinforcement Learning (unknown): “Although similar methods have also been applied to transfer learning, most of these learn task-relevant representations for SL [2,5] or RL [18,30,37,40,60,70,75,83]; the latter aim to reduce the state space of the target task, or find good representations for value functions or policies.”
Measuring the Distance Between Finite Markov Decision Processes (2016, methodology): “We consider the maze problem in which many transfer learning methods have been applied [8, 9, 20].”