Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
96
datasets available to search
ShareScore release 0.7.1
Dataset results
96 results for “Reinforcement Learning”
Data from: Reinforcement learning-based framework for whale rendezvous via autonomous sensing robots
Open the record for dataset details and reuse information.
Reaching the limit in autonomous racing: Optimal control versus reinforcement learning
Open the record for dataset details and reuse information.
The AI Economist: Taxation policy design via two-level deep reinforcement learning
Open the record for dataset details and reuse information.
Reinforcement learning theory reveals the cognitive requirements for solving the cleaner fish market task
Open the record for dataset details and reuse information.
Release of the systematic literature review into Reinforcement Learning for personalization
<p>Release of the systematic literature review into Reinforcement Learning for personalization</p>
Supplementary video of the paper "Robotic Object Sorting via Deep Reinforcement Learning: a generalized approach"
<p>Supplementary video of the paper "Robotic Object Sorting via Deep Reinforcement Learning: a generalized approach" showing the experimental results.</p>
Dataset for "Meta-reinforcement learning via orbitofrontal cortex"
<p>Neural and behavioral dataset for <a href="https://doi.org/10.1038/s41593-023-01485-3">"Meta-reinforcement learning via orbitofrontal cortex" published in Nature Neuroscience</a>.<br><br>The zip file includes 3 folders: "Imaging", "Inactivation", "paAIP2"</p> <p><em><strong>"Imaging"</strong></em><br>Datasets are separated into different folders based on the mouse name (e.g. RH365) and imaging plane (deeper or shallower). Each data file in .npz format contains the following variables:<br><strong>zSR_readystart</strong>: OFC neural population activity. Deconvolved calcium signals are aligned to a ready cue onset and saved in 3d tensor format ([Neuron ID] x [Frames] x [Trials]). Neural activity of 10 sec before and 14 sec after the ready cue onset is included.<br><strong>SR_fps</strong>: Frame rate of neural activity data (frame per sec).<br><strong>pre_ready_sec</strong>: Pre-ready onset time (10 sec) included in zSR_readystart.<br><strong>post_ready_sec</strong>: Post-ready onset time (14 sec) included in zSR_readystart.<br><strong>pre_ready_frame</strong>: Pre-ready onset frames included in zSR_readystart. The frame number corresponds to pre_ready_sec.<br><strong>post_ready_frame</strong>: Post-ready onset frames included in zSR_readystart. The frame number corresponds to post_ready_sec.<br><strong>Ready2Ans_frameSR</strong>: Frame number from ready cue onset to go cue. This can be used to re-align activity to go cue onset.<br><strong>Ready2Choice_frameSR</strong>: Frame number from ready cue onset to choice. This can be used to re-align activity to choice onset.<br><strong>Trials4Use</strong>: Trial numbers (begins from 0) with good imaging quality. Use only these trials for neural activity analyses.<br><strong>a</strong>: Actions of mice during behavioral session. 1: right choice, 2: left choice, 3: alarm trial, 4: miss trial<br><strong>R</strong>: Reward outcomes during behavioral session. 1: reward, 0: no-reward<br><strong>rprob</strong>: Reward assignment probability on right side in each trial.<br><strong>lprob</strong>: Reward assignment probability on left side in each trial.</p> <p><em><strong>"Inactivation"</strong></em><br>Datasets for optogenetic OFC inactivation experiments. Datasets are separated into different folders based on experiment type (Bilateral or Unilateral OFC inactivation), mouse type (e.g. ChrimsonR, tdTomato control), illumination type (e.g. iti_2sec, ready), and the mouse name (e.g. RH895). Each data file in .npz format contains the following variables:<br><strong>a</strong>: Actions of mice during behavioral session. 1: right choice, 2: left choice, 3: alarm trial, 4: miss trial<br><strong>R</strong>: Reward outcomes during behavioral session. 1: reward, 0: no-reward<br><strong>Opto</strong>: 1: inactivation trials, 0: masking light only<br><strong>rprob</strong>: Reward assignment probability on right side in each trial.<br><strong>lprob</strong>: Reward assignment probability on left side in each trial.</p> <p><em><strong>"paAIP2"</strong></em><br>Datasets for OFC plasticity suppression experiments. Datasets are separated into different folders based on experiment type (Suppression at expert or during training), mouse type (e.g. paAIP2 or Control), and the mouse name (e.g. RH923). Each data file in .npz format contains the following variables:<br><strong>a</strong>: Actions of mice during behavioral session. 1: right choice, 2: left choice, 3: alarm trial, 4: miss trial<br><strong>R</strong>: Reward outcomes during behavioral session. 1: reward, 0: no-reward<br><strong>rprob</strong>: Reward assignment probability on right side in each trial.<br><strong>lprob</strong>: Reward assignment probability on left side in each trial.</p> <p>Details of the datasets and experimental conditions are described in the publication (<a href="https://doi.org/10.1038/s41593-023-01485-3">Hattori et al., Meta-reinforcement learning via orbitofrontal cortex, Nature Neuroscience, 2023</a>).</p> <p><br><em>There was a report that Mac users may get "extra bytes at beginning" error when trying to unzip the file. A solution to this problem was to run "zip -FFv foo.zip --out fixed.zip" where foo.zip is the path of the file downloaded from Zenodo. Then, run "unzip fixed.zip".</em></p>
Personalize E-Commerce Product Recommendations Based on User Behavior Using Reinforced Learning Algorithms
<p><span>The development of a personalized and adaptive e-commerce product recommendation system will be developed using the Reinforcement Learning algorithm in this study. Initial data is extremely promising in its ability to raise sales conversion: 30% of the products added to the cart are never purchased. Additionally, there is a strong correlation of 0.8 between viewed versus purchased products. Data collection was from 447 Indonesian respondents over a period of June to July 2024. It was collected using an online questionnaire that measures recommendation quality, satisfaction, and ease of use with purposive sampling. Partial Least Squares Structural Equation Modeling was done on the data analysis. From that, it has been found that system quality is positively related to the accuracy, novelty, and diversity of the recommendation. The results further show how this would lead to an improved user experience, satisfaction, and sales conversion with the reinforcement learning-based system. These findings give insight into developing efficient adaptive recommendation systems on e-commerce platforms and open opportunities for further research. </span></p>
Automated inference of sequences of operations in RESTful APIs with deep reinforcement learning - replication package
<p>This directory contains the replication package of the article entitled "Automated inference of sequences of operations in RESTful APIs with deep reinforcement learning". Please note that this is NOT a real publication or scientific report, but a project created for the purpose of learning the basic concepts of research by emulating the process of creating an article.</p>
Mutation Testing of Deep Reinforcement Learning Based on Real Faults
<p>Trained agents to be used in the replication package of the paper "<em>Mutation Testing of Deep Reinforcement Learning Based on Real Faults</em>" accepted to the International Conference on Software Testing (ICST) 2023. The replication package is at https://github.com/FlowSs/RLMutation.</p>
Dataset for Automated Unit Test Generation via Chain of Thought Prompt and Reinforcement Learning
<p>This is the replication package including three types datasets: training dataset with CoT prompts, reward dataset for training reward model, rl dataset for optimizing policy model. The training dataset includes filter_test_cot_rule_50k.csv, filter_train_cot_rule_50k.csv, and filter_valid_cot_rule_50k.csv. These three datasets includes multiple fields (i.e., src_fm, intention, plan, elaboration, gpt_test, src_fm_cot_gpt, target, src_fm_fc_ms_ff,src_fm_intention,src_fm_plan,src_fm_elaboration,idx,rule_cot,rule_cot_nlp,combine_cot,src_fm_rule_cot_nlp,src_fm_cot_nlp_gpt,gpt_cot_filter,src_fm_plan_intention). The reward dataset includes test_athena.json, train_athena.json, and valid_athena.json three files. The rl dataset includes three files: filter_test_cot_gpt_rl.csv, filter_train_cot_gpt_rl.csv, filter_valid_cot_gpt_rl.csv. These files include mulitple fields: src_fm,intention,plan,elaboration,gpt_test,src_fm_cot_gpt,target,src_fm_fc_ms_ff,src_fm_intention,src_fm_plan,src_fm_elaboration,gpt_cot_filter.</p>
Exploring Clustering Techniques for Effective Reinforcement Learning based Personalization for Health and Wellbeing/Database 1
<p>The first Dataset of the five runs done. If you would like to have access to any or all of the others please send an e-mail to the authors.</p>
FreeCiv games played by Knowledge-based Reinforcement Learning
<p>The dataset contains 600 fully played games of FreeCiv game. </p>
Reinforcement Learning in path-dependent, non-ergodic contexts
<p>Data and models for training reinforcement learning agents in path-dependent, non-ergodic context. Provided to support our paper (reference upon publication)</p>
Replication Package for "Using Reinforcement Learning to Sustain the Performance of Version Control Repositories"
<p>The replication package is organized into two containers, each of which is responsible for reproducing figures and analyses for each RQ.</p> <p>## Decompress Package</p> <p>```<br>$ tar -xvJf rl4monorepos.tar.xz<br>```</p> <p>## RQ1</p> <p>1. Import the container</p> <p>```<br>$ docker import rq1.tar rq1<br>```</p> <p>2. Regenerate figures</p> <p>```<br>$ docker container run -v <outputdir>:/out -e R_SCRIPT=figures.R rq1 <br>```</p> <p>3. Re-execute statistical tests</p> <p>```<br>$ docker container run -e R_SCRIPT=stats-test.R rq1<br>```</p> <p>## RQ2</p> <p>1. Import the container</p> <p>```<br>$ docker import rq2.tar rq2<br>```</p> <p>2. Regenerate figures and print AUC values</p> <p>```<br>$ docker container run -v <outputdir>:/out -e R_SCRIPT=figures.R rq2 <br>```</p>
Data and code for "Compulsivity is linked to suboptimal choice variability but unaltered reinforcement learning under uncertainty"
<p>Data and code for "Compulsivity is linked to suboptimal choice variability but unaltered reinforcement learning under uncertainty". See https://github.com/jlexternal/RLVOLUNP_CIT_ana for directory structure. </p>
Supplementary Data "Robustness and Generalization in Quantum Reinforcement Learning via Lipschitz Regularization"
<p>Pe-computed data for re-producing the results of "Robustness and Generalization in Quantum<br>Reinforcement Learning via Lipschitz Regularization".</p> <p>See also the GitHub repository https://github.com/nicomeyer96/regularized-qpg </p>
Figure Data for the paper "Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning"
<p><strong>Data Release for Article: <em>Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning</em></strong></p> <p>This package releases a Python notebook reproducing the quantitative<br> figures featured in the research article "Mastering the Game of Stratego with <br> Model-Free Multiagent Reinforcement Learning".</p> <p><strong>Usage</strong></p> <p>The notebook can be uploaded to and executed using the<br> [Colab](https://colab.research.google.com) runtime service. <br> The Python notebook is tested against Python `3.7`.</p> <p><strong>License and disclaimer</strong></p> <p>Copyright 2022 DeepMind Technologies Limited</p> <p>All software is licensed under the Apache License, Version 2.0 (Apache 2.0); you<br> may not use this file except in compliance with the Apache 2.0 license. You may<br> obtain a copy of the Apache 2.0 license at:<br> https://www.apache.org/licenses/LICENSE-2.0</p> <p>All other materials are licensed under the Creative Commons Attribution 4.0<br> International License (CC-BY). You may obtain a copy of the CC-BY license at:<br> https://creativecommons.org/licenses/by/4.0/legalcode</p> <p>Unless required by applicable law or agreed to in writing, all software and<br> materials distributed here under the Apache 2.0 or CC-BY licenses are<br> distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,<br> either express or implied. See the licenses for the specific language governing<br> permissions and limitations under those licenses.</p> <p>This is not an official Google product.</p>
Champion-Level Drone Racing using Deep Reinforcement Learning: Supplementary Data
<p>Supplementary data for the publication "Champion-Level Drone Racing using Deep Reinforcement Learning".</p> <p>racing_data.zip: The data includes the recorded position of human and autonomous drones during head-to-head races and time-trial runs. The included code provides plotting and statistical analysis of the data.</p> <p>pseudocode.zip: Pseudocode that illustrates gate detection, VIO drift estimation, policy training, and residual model identification.</p>
Reinforcement learning prioritizes general applicability in reaction optimization - optimization data logs
<p>A zipped file of all optimization data logs for publication "Reinforcement learning prioritizes general applicability in reaction optimization". Included in the files are: acquisition logs for simulation testing with synthetic data, simulation testing with various chemistry datasets and a real time amide coupling optimization</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.