Rlpy: A Value-Function-Based Reinforcement Learning Framework for Education and Research
RLPy is an object-oriented reinforcement learning software package with a focus on valuefunction-based methods using linear function approximation and discrete actions. The framework was designed for both educational and research purposes. It provides a rich library of fine-grained, easily exchangea...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
MIT Press
2016
|
| Online Access: | http://hdl.handle.net/1721.1/105742 https://orcid.org/0000-0002-2508-1957 |
| _version_ | 1826215517667459072 |
|---|---|
| author | Dann, Christoph Dabney, William Geramifard, Alborz Klein, Robert Henry How, Jonathan P. |
| author2 | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems |
| author_facet | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Dann, Christoph Dabney, William Geramifard, Alborz Klein, Robert Henry How, Jonathan P. |
| author_sort | Dann, Christoph |
| collection | MIT |
| description | RLPy is an object-oriented reinforcement learning software package with a focus on valuefunction-based methods using linear function approximation and discrete actions. The framework was designed for both educational and research purposes. It provides a rich library of fine-grained, easily exchangeable components for learning agents (e.g., policies or representations of value functions), facilitating recently increased specialization in reinforcement learning. RLPy is written in Python to allow fast prototyping, but is also suitable for large-scale experiments through its built-in support for optimized numerical libraries and parallelization. Code profiling, domain visualizations, and data analysis are integrated in a self-contained package available under the Modified BSD License at
http://github.com/rlpy/rlpy. All of these properties allow users to compare various reinforcement learning algorithms with little effort. |
| first_indexed | 2024-09-23T16:32:52Z |
| format | Article |
| id | mit-1721.1/105742 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:32:52Z |
| publishDate | 2016 |
| publisher | MIT Press |
| record_format | dspace |
| spelling | mit-1721.1/1057422022-09-29T20:08:03Z Rlpy: A Value-Function-Based Reinforcement Learning Framework for Education and Research Dann, Christoph Dabney, William Geramifard, Alborz Klein, Robert Henry How, Jonathan P. Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Geramifard, Alborz Klein, Robert Henry How, Jonathan P. RLPy is an object-oriented reinforcement learning software package with a focus on valuefunction-based methods using linear function approximation and discrete actions. The framework was designed for both educational and research purposes. It provides a rich library of fine-grained, easily exchangeable components for learning agents (e.g., policies or representations of value functions), facilitating recently increased specialization in reinforcement learning. RLPy is written in Python to allow fast prototyping, but is also suitable for large-scale experiments through its built-in support for optimized numerical libraries and parallelization. Code profiling, domain visualizations, and data analysis are integrated in a self-contained package available under the Modified BSD License at http://github.com/rlpy/rlpy. All of these properties allow users to compare various reinforcement learning algorithms with little effort. 2016-12-07T19:45:44Z 2016-12-07T19:45:44Z 2015-08 2014-11 Article http://purl.org/eprint/type/JournalArticle 1532-4435 1533-7928 http://hdl.handle.net/1721.1/105742 Geramifard, Alborz et al. "RLPy: A Value-Function-Based Reinforcement Learning Framework for Education and Research." Journal of Machine Learning Research 16 (2015):1573−1578. https://orcid.org/0000-0002-2508-1957 en_US http://jmlr.org/papers/v16/geramifard15a.html Journal of Machine Learning Research Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf MIT Press MIT Press |
| spellingShingle | Dann, Christoph Dabney, William Geramifard, Alborz Klein, Robert Henry How, Jonathan P. Rlpy: A Value-Function-Based Reinforcement Learning Framework for Education and Research |
| title | Rlpy: A Value-Function-Based Reinforcement Learning Framework for Education and Research |
| title_full | Rlpy: A Value-Function-Based Reinforcement Learning Framework for Education and Research |
| title_fullStr | Rlpy: A Value-Function-Based Reinforcement Learning Framework for Education and Research |
| title_full_unstemmed | Rlpy: A Value-Function-Based Reinforcement Learning Framework for Education and Research |
| title_short | Rlpy: A Value-Function-Based Reinforcement Learning Framework for Education and Research |
| title_sort | rlpy a value function based reinforcement learning framework for education and research |
| url | http://hdl.handle.net/1721.1/105742 https://orcid.org/0000-0002-2508-1957 |
| work_keys_str_mv | AT dannchristoph rlpyavaluefunctionbasedreinforcementlearningframeworkforeducationandresearch AT dabneywilliam rlpyavaluefunctionbasedreinforcementlearningframeworkforeducationandresearch AT geramifardalborz rlpyavaluefunctionbasedreinforcementlearningframeworkforeducationandresearch AT kleinroberthenry rlpyavaluefunctionbasedreinforcementlearningframeworkforeducationandresearch AT howjonathanp rlpyavaluefunctionbasedreinforcementlearningframeworkforeducationandresearch |