Timezone: »
Poster
Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining
George Konidaris · Andrew G Barto
We introduce skill chaining, a skill discovery method for reinforcement learning agents in continuous domains, that builds chains of skills leading to an end-of-task reward. We demonstrate experimentally that it creates skills that result in performance benefits in a challenging continuous domain.
Author Information
George Konidaris (Brown University)
Andrew G Barto (University of Massachusetts)
Related Events (a corresponding poster, oral, or spotlight)
-
2009 Spotlight: Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining »
Thu. Dec 10th 01:14 -- 01:15 AM Room
More from the Same Authors
-
2021 : Bayesian Exploration for Lifelong Reinforcement Learning »
Haotian Fu · Shangqun Yu · Michael Littman · George Konidaris -
2021 Poster: Learning Markov State Abstractions for Deep Reinforcement Learning »
Cameron Allen · Neev Parikh · Omer Gottesman · George Konidaris -
2017 Workshop: Hierarchical Reinforcement Learning »
Andrew G Barto · Doina Precup · Shie Mannor · Tom Schaul · Roy Fox · Carlos Florensa -
2011 Poster: TD_gamma: Re-evaluating Complex Backups in Temporal Difference Learning »
George Konidaris · Scott Niekum · Philip Thomas -
2011 Poster: Clustering via Dirichlet Process Mixture Models for Portable Skill Discovery »
Scott Niekum · Andrew G Barto -
2010 Poster: Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories »
George Konidaris · Scott R Kuindersma · Andrew G Barto · Roderic A Grupen -
2008 Poster: Skill Characterization Based on Betweenness »
Özgür Şimşek · Andrew G Barto -
2007 Workshop: Hierarchical Organization of Behavior: Computational, Psychological and Neural Perspectives (Part 2) »
Yael Niv · Matthew Botvinick · Andrew G Barto -
2007 Workshop: Hierarchical Organization of Behavior: Computational, Psychological and Neural Perspectives (Part 1) »
Yael Niv · Matthew Botvinick · Andrew G Barto