Issues in putting reinforcement learning onto robots:
Abstract: "There has recently been a good deal of interest in robot learning. Reinforcement Learning (RL) is a trial and error approach to learning that has recently become popular with roboticists. This is despite the fact that RL methods are very slow, and scale badly with the size of the sta...
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Edinburgh
1996
|
| Series: | University <Edinburgh> / Department of Artificial Intelligence: DAI research paper
784 |
| Subjects: | |
| Summary: | Abstract: "There has recently been a good deal of interest in robot learning. Reinforcement Learning (RL) is a trial and error approach to learning that has recently become popular with roboticists. This is despite the fact that RL methods are very slow, and scale badly with the size of the state and action spaces, thus making them difficult to put onto real robots. This paper describes some work I have been doing on trying to understand why RL methods are so slow and on how they might be speeded up. A reinforcement learning algorithm loosely based on the theory of hypothesis testing is presented as are some preliminary results from employing this algorithm on a set of bandit problems." |
| Physical Description: | 8 S. |
Staff View
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV011049422 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 961111s1996 |||| 00||| engod | ||
| 035 | |a (OCoLC)35590613 | ||
| 035 | |a (DE-599)BVBBV011049422 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-91G | ||
| 100 | 1 | |a Wyatt, Jeremy |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Issues in putting reinforcement learning onto robots |c Wyaatt, J. |
| 264 | 1 | |a Edinburgh |c 1996 | |
| 300 | |a 8 S. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a University <Edinburgh> / Department of Artificial Intelligence: DAI research paper |v 784 | |
| 520 | 3 | |a Abstract: "There has recently been a good deal of interest in robot learning. Reinforcement Learning (RL) is a trial and error approach to learning that has recently become popular with roboticists. This is despite the fact that RL methods are very slow, and scale badly with the size of the state and action spaces, thus making them difficult to put onto real robots. This paper describes some work I have been doing on trying to understand why RL methods are so slow and on how they might be speeded up. A reinforcement learning algorithm loosely based on the theory of hypothesis testing is presented as are some preliminary results from employing this algorithm on a set of bandit problems." | |
| 650 | 7 | |a Bionics and artificial intelligence |2 sigle | |
| 650 | 7 | |a Robotics and its application |2 sigle | |
| 650 | 4 | |a Algorithms | |
| 650 | 4 | |a Hypothesis | |
| 650 | 4 | |a Reinforcement learning | |
| 650 | 4 | |a Robots |x Control systems | |
| 810 | 2 | |a Department of Artificial Intelligence: DAI research paper |t University <Edinburgh> |v 784 |w (DE-604)BV010450646 |9 784 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-007399894 | ||
Record in the Search Index
| _version_ | 1804125539070377984 |
|---|---|
| any_adam_object | |
| author | Wyatt, Jeremy |
| author_facet | Wyatt, Jeremy |
| author_role | aut |
| author_sort | Wyatt, Jeremy |
| author_variant | j w jw |
| building | Verbundindex |
| bvnumber | BV011049422 |
| ctrlnum | (OCoLC)35590613 (DE-599)BVBBV011049422 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01828nam a2200349 cb4500</leader><controlfield tag="001">BV011049422</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">961111s1996 |||| 00||| engod</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)35590613</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV011049422</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91G</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Wyatt, Jeremy</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Issues in putting reinforcement learning onto robots</subfield><subfield code="c">Wyaatt, J.</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Edinburgh</subfield><subfield code="c">1996</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">8 S.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">University <Edinburgh> / Department of Artificial Intelligence: DAI research paper</subfield><subfield code="v">784</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "There has recently been a good deal of interest in robot learning. Reinforcement Learning (RL) is a trial and error approach to learning that has recently become popular with roboticists. This is despite the fact that RL methods are very slow, and scale badly with the size of the state and action spaces, thus making them difficult to put onto real robots. This paper describes some work I have been doing on trying to understand why RL methods are so slow and on how they might be speeded up. A reinforcement learning algorithm loosely based on the theory of hypothesis testing is presented as are some preliminary results from employing this algorithm on a set of bandit problems."</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Bionics and artificial intelligence</subfield><subfield code="2">sigle</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Robotics and its application</subfield><subfield code="2">sigle</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Algorithms</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hypothesis</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Reinforcement learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Robots</subfield><subfield code="x">Control systems</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">Department of Artificial Intelligence: DAI research paper</subfield><subfield code="t">University <Edinburgh></subfield><subfield code="v">784</subfield><subfield code="w">(DE-604)BV010450646</subfield><subfield code="9">784</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-007399894</subfield></datafield></record></collection> |
| id | DE-604.BV011049422 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-09T18:03:10Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-007399894 |
| oclc_num | 35590613 |
| open_access_boolean | |
| owner | DE-91G DE-BY-TUM |
| owner_facet | DE-91G DE-BY-TUM |
| physical | 8 S. |
| publishDate | 1996 |
| publishDateSearch | 1996 |
| publishDateSort | 1996 |
| record_format | marc |
| series2 | University <Edinburgh> / Department of Artificial Intelligence: DAI research paper |
| spelling | Wyatt, Jeremy Verfasser aut Issues in putting reinforcement learning onto robots Wyaatt, J. Edinburgh 1996 8 S. txt rdacontent n rdamedia nc rdacarrier University <Edinburgh> / Department of Artificial Intelligence: DAI research paper 784 Abstract: "There has recently been a good deal of interest in robot learning. Reinforcement Learning (RL) is a trial and error approach to learning that has recently become popular with roboticists. This is despite the fact that RL methods are very slow, and scale badly with the size of the state and action spaces, thus making them difficult to put onto real robots. This paper describes some work I have been doing on trying to understand why RL methods are so slow and on how they might be speeded up. A reinforcement learning algorithm loosely based on the theory of hypothesis testing is presented as are some preliminary results from employing this algorithm on a set of bandit problems." Bionics and artificial intelligence sigle Robotics and its application sigle Algorithms Hypothesis Reinforcement learning Robots Control systems Department of Artificial Intelligence: DAI research paper University <Edinburgh> 784 (DE-604)BV010450646 784 |
| spellingShingle | Wyatt, Jeremy Issues in putting reinforcement learning onto robots Bionics and artificial intelligence sigle Robotics and its application sigle Algorithms Hypothesis Reinforcement learning Robots Control systems |
| title | Issues in putting reinforcement learning onto robots |
| title_auth | Issues in putting reinforcement learning onto robots |
| title_exact_search | Issues in putting reinforcement learning onto robots |
| title_full | Issues in putting reinforcement learning onto robots Wyaatt, J. |
| title_fullStr | Issues in putting reinforcement learning onto robots Wyaatt, J. |
| title_full_unstemmed | Issues in putting reinforcement learning onto robots Wyaatt, J. |
| title_short | Issues in putting reinforcement learning onto robots |
| title_sort | issues in putting reinforcement learning onto robots |
| topic | Bionics and artificial intelligence sigle Robotics and its application sigle Algorithms Hypothesis Reinforcement learning Robots Control systems |
| topic_facet | Bionics and artificial intelligence Robotics and its application Algorithms Hypothesis Reinforcement learning Robots Control systems |
| volume_link | (DE-604)BV010450646 |
| work_keys_str_mv | AT wyattjeremy issuesinputtingreinforcementlearningontorobots |