A: The sequence learning setup.
<p>In the full task, the student is required to take a sequence of <i>N</i> correct actions to get reward. In intermediate levels of the task, the reward is delivered if the student takes correct actions. is the innate bias of the student to take the correct action at the <i>...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852016644440719360 |
|---|---|
| author | William L. Tong (22238845) |
| author2 | Venkatesh N. Murthy (15354261) Gautam Reddy (11927277) |
| author2_role | author author |
| author_facet | William L. Tong (22238845) Venkatesh N. Murthy (15354261) Gautam Reddy (11927277) |
| author_role | author |
| dc.creator.none.fl_str_mv | William L. Tong (22238845) Venkatesh N. Murthy (15354261) Gautam Reddy (11927277) |
| dc.date.none.fl_str_mv | 2025-09-12T18:03:21Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pcbi.1013454.g002 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/A_The_sequence_learning_setup_/30117319 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Neuroscience Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> dogs starting point towards monte carlo planning student &# 8217 sequence learning task previously assigned tasks perform complex tasks general computational framework adaptive shaping heuristic student framework shaping behavior navigation tasks harder tasks adaptive algorithms work provides using algorithms task based minimal parameters laboratory mice involve sparse delayed rewards continuous curricula commonly trained careful balance adaptively alternate |
| dc.title.none.fl_str_mv | A: The sequence learning setup. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <p>In the full task, the student is required to take a sequence of <i>N</i> correct actions to get reward. In intermediate levels of the task, the reward is delivered if the student takes correct actions. is the innate bias of the student to take the correct action at the <i>i</i>th step, prior to training. We assume for all <i>i</i> unless otherwise specified. B: The incremental teacher (INC) fails once . C: The <i>q</i> values (in grayscale) for the correct action at each step shown for (top) and (bottom). The red line shows the assigned task level. Note the striped dynamics in the top row caused due to alternating reinforcement and extinction. In the bottom row, <i>ε</i> is too small, forcing learning to stall. D: Time series of <i>q</i> values for actions at the first (solid black) and third (dashed gray) steps for the two examples shown in panel C.</p> |
| eu_rights_str_mv | openAccess |
| id | Manara_9088eaa5c1db997b9b60ff453740cf7e |
| identifier_str_mv | 10.1371/journal.pcbi.1013454.g002 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30117319 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | A: The sequence learning setup.William L. Tong (22238845)Venkatesh N. Murthy (15354261)Gautam Reddy (11927277)NeuroscienceScience PolicyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedxlink "> dogsstarting point towardsmonte carlo planningstudent &# 8217sequence learning taskpreviously assigned tasksperform complex tasksgeneral computational frameworkadaptive shaping heuristicstudent frameworkshaping behaviornavigation tasksharder tasksadaptive algorithmswork providesusing algorithmstask basedminimal parameterslaboratory miceinvolve sparsedelayed rewardscontinuous curriculacommonly trainedcareful balanceadaptively alternate<p>In the full task, the student is required to take a sequence of <i>N</i> correct actions to get reward. In intermediate levels of the task, the reward is delivered if the student takes correct actions. is the innate bias of the student to take the correct action at the <i>i</i>th step, prior to training. We assume for all <i>i</i> unless otherwise specified. B: The incremental teacher (INC) fails once . C: The <i>q</i> values (in grayscale) for the correct action at each step shown for (top) and (bottom). The red line shows the assigned task level. Note the striped dynamics in the top row caused due to alternating reinforcement and extinction. In the bottom row, <i>ε</i> is too small, forcing learning to stall. D: Time series of <i>q</i> values for actions at the first (solid black) and third (dashed gray) steps for the two examples shown in panel C.</p>2025-09-12T18:03:21ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pcbi.1013454.g002https://figshare.com/articles/figure/A_The_sequence_learning_setup_/30117319CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/301173192025-09-12T18:03:21Z |
| spellingShingle | A: The sequence learning setup. William L. Tong (22238845) Neuroscience Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> dogs starting point towards monte carlo planning student &# 8217 sequence learning task previously assigned tasks perform complex tasks general computational framework adaptive shaping heuristic student framework shaping behavior navigation tasks harder tasks adaptive algorithms work provides using algorithms task based minimal parameters laboratory mice involve sparse delayed rewards continuous curricula commonly trained careful balance adaptively alternate |
| status_str | publishedVersion |
| title | A: The sequence learning setup. |
| title_full | A: The sequence learning setup. |
| title_fullStr | A: The sequence learning setup. |
| title_full_unstemmed | A: The sequence learning setup. |
| title_short | A: The sequence learning setup. |
| title_sort | A: The sequence learning setup. |
| topic | Neuroscience Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> dogs starting point towards monte carlo planning student &# 8217 sequence learning task previously assigned tasks perform complex tasks general computational framework adaptive shaping heuristic student framework shaping behavior navigation tasks harder tasks adaptive algorithms work provides using algorithms task based minimal parameters laboratory mice involve sparse delayed rewards continuous curricula commonly trained careful balance adaptively alternate |