Using Options for Knowledge Transfer in Reinforcement Learning
By Theodore J. Perkins, Doina Precup. 1999
Subfields: Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Reinforcement Learning
- Sergey Levine
- Pieter Abbeel
- George Dimitri Konidaris
- Shixiang Shane Gu
- Chelsea Finn
- Ofir Nachum
- Vikash Kumar
- Doina Precup
Citations in the corpus
- Dynamics-Aware Unsupervised Discovery of Skills (2019, background): “This ranges from the classic option-critic architecture [66, 65, 55] to some of the more recent work [7, 70, 48, 29].”
- Transfer in Reinforcement Learning via Shared Features (2012, background): “Other research has focused on extracting options by exploiting commonalities in collections of policies over a single state space (Thrun and Schwartz, 1995; Bernstein, 1999; Perkins and Precup, 1999; Pickett and Barto, 2002).”
- Transfer in Reinforcement Learning: A Framework and a Survey (2012, methodology): “Options are used to speed-up learning also in (Perkins and Precup, 1999) where a POMDP-like framework is considered.”
- Building Portable Options: Skill Transfer in Reinforcement Learning (2007, background): “…is distinct from that taken in prior reinforcement learning research on finding useful macro-actions across sequences of tasks [Bernstein, 1999; Perkins & Precup, 1999; Pickett & Barto, 2002; Thrun & Schwartz, 1995], where the tasks must be in the same state space but may have different reward…”
- Using Bisimulation for Policy Transfer in MDPs (2010, background): “Previous work has also illustrated the fact that using temporally extended actions (and their models) can significantly improve knowledge transfer in MDPs (e.g., Perkins & Precup, 1999, Andre & Russell, 2002; Ravindran & Barto, 2003; Konidaris & Barto, 2007).”
- Transfer Learning for Reinforcement Learning Domains: A Survey (2009, unknown): “A different problem formulation is posed by Perkins and Precup (1999)where the transition function,T, may change after reaching the goal.”
- Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining (2009, methodology): “Finally, some methods extract options by exploiting commonalities in collections of policies over a single state space [14, 15, 16, 17].”