Task: reinforcement-learning
933 datasets. Listed here: 877 of them, most downloaded first. Page 4 of 5.
- ReactiveAI/TinyStories-MRLPermissive or share-alikeapache-2.0129 downloads in 30 days
- rhstephens/hive-player-gamesPermissive or share-alikemit129 downloads in 30 days
- Arc-Intelligence/arc-crm-benchmarkPermissive or share-alikemit128 downloads in 30 days
- yethdev/2048-gameplay-datasetUnclearother128 downloads in 30 days
- ayjays132/AI_Mastery_Foundation_CurriculumPermissive or share-alikecc-by-4.0127 downloads in 30 days
- thesisDeath/blood-pathology-lims-environmentPermissive or share-alikecc-by-4.0127 downloads in 30 days
- Sashvat/HyperThink-X-Nvidia-Opencode-Reasoning-200KPermissive or share-alikecc-by-4.0126 downloads in 30 days
- aarontung/testPermissive or share-alikecc-by-sa-4.0126 downloads in 30 days
- jasonyandell/texas-42-walt-pourPermissive or share-alikecc0-1.0126 downloads in 30 days
- vibrantlabsai/usaspending-reconPermissive or share-alikecc0-1.0126 downloads in 30 days
- AgentNativeResearchLab/arc-agi3-agy-gemini3.1pro-r11lPermissive or share-alikecc-by-4.0125 downloads in 30 days
- solsticestudioai/frontier-robotics-packPermissive or share-alikecc-by-4.0125 downloads in 30 days
- vibrantlabsai/terminal-deskPermissive or share-alikeodc-by125 downloads in 30 days
- AutoLab-SJTU/RoboCombinePermissive or share-alikecc-by-4.0124 downloads in 30 days
- VaidikML0508/mystery-agent-casesPermissive or share-alikeapache-2.0124 downloads in 30 days
- SnehShah/house-md-sft-dataPermissive or share-alikeapache-2.0123 downloads in 30 days
- coslinedev/financial-rlvr-10k-enterprisePermissive or share-alikemit123 downloads in 30 days
- eagle0504/multireward-grpo-gsm8k-rewardsPermissive or share-alikecc-by-4.0123 downloads in 30 days
- Suchenl/Robot-Customization-AssetsPermissive or share-alikeapache-2.0122 downloads in 30 days
- sshpunk/polymarket-quant-deskPermissive or share-alikemit121 downloads in 30 days
- AgentNativeResearchLab/arc-agi3-agy-kimi2.7-thinking-ft09Permissive or share-alikecc-by-4.0119 downloads in 30 days
- IntelligenceLab/Cos-Play-Cold-StartPermissive or share-alikemit119 downloads in 30 days
- jaehyeokdoo2/flow-edit-cube-triple-tkgrid-seeds30003-40004Permissive or share-alikemit119 downloads in 30 days
- james77mill/chessbench-encoded-npzPermissive or share-alikecc-by-4.0119 downloads in 30 days
- Groovy-123/QuantumAIPermissive or share-alikeapache-2.0118 downloads in 30 days
- dbsgh797210/SOLAR-extrasPermissive or share-alikeapache-2.0118 downloads in 30 days
- hbveom/24ikdnmzPermissive or share-alikecc-by-4.0118 downloads in 30 days
- Liang-ZX/DexHandDiff-ManipulateBlockPermissive or share-alikemit117 downloads in 30 days
- webxos/matrix_operationsPermissive or share-alikeapache-2.0117 downloads in 30 days
- guanzhong2/TU_PipelinePermissive or share-alikecc-by-4.0116 downloads in 30 days
- ultrastar111/sokoban_easy_v8_noncot_chunk_k5_world_model_20260622_persegUse restrictionscc-by-nc-4.0116 downloads in 30 days
- AlignmentResearch/boxoban-astar-solutionsPermissive or share-alikeapache-2.0115 downloads in 30 days
- JoshPurtell/nanohorizon-craftax-v5Permissive or share-alikeapache-2.0114 downloads in 30 days
- jonhlin/stg-rl-train-envsPermissive or share-alikeapache-2.0114 downloads in 30 days
- MinghaoFu/lewm-originalPermissive or share-alikemit113 downloads in 30 days
- patnir41/kaetram-qwen-rolloutsPermissive or share-alikeapache-2.0113 downloads in 30 days
- Vishal0407/GSM8K_TAMILPermissive or share-alikemit112 downloads in 30 days
- open-athena/nemotron-gym-agent-workplacePermissive or share-alikecc-by-4.0112 downloads in 30 days
- spade-rl/SPADE-Environment-Pool-GPT5.5-ToolUseUnclearother111 downloads in 30 days
- Zachzzz33/Smart-shower-usage-datasetPermissive or share-alikemit110 downloads in 30 days
- Karesis/GoDatasPermissive or share-alikeapache-2.0108 downloads in 30 days
- Seyidia/satranc-verisiPermissive or share-alikemit108 downloads in 30 days
- patnir41/kaetram-opd-2bPermissive or share-alikeapache-2.0107 downloads in 30 days
- Blaze2oi/stock-datasetPermissive or share-alikemit106 downloads in 30 days
- Jacqkues/kev-vision-decisions-fullUnclearother106 downloads in 30 days
- PowerZooJax/PowerZooDatasetUnclearother106 downloads in 30 days
- allen73/microduck-trajectory-datasetPermissive or share-alikemit106 downloads in 30 days
- amsks/factoredfb-metaworld-playPermissive or share-alikemit106 downloads in 30 days
- jometeorie/urbanground-tasksPermissive or share-alikemit105 downloads in 30 days
- vibrantlabsai/pool-desk-v6Possible licence conflictother104 downloads in 30 days
- PTeterwak/openwebrl-arm-matched-pairsUnclearother103 downloads in 30 days
- Torch-Trade/btcusdt_spot_1m_03_2023_to_03_2026Permissive or share-alikemit103 downloads in 30 days
- eachsheep/EvoDev-BenchUse restrictionscc-by-nc-4.0103 downloads in 30 days
- obaydata/world-model-gameplay-recordingUse restrictionscc-by-nc-4.0103 downloads in 30 days
- vosldtgbj/project-llm-dataset-rlvr-unified-v2-37500Unclearother103 downloads in 30 days
- RegalFire/GameAgent-Recovery-100KPermissive or share-alikemit102 downloads in 30 days
- benni-ben/SatireInstructPermissive or share-alikemit102 downloads in 30 days
- originlab/game-recordings-v3Unclearother102 downloads in 30 days
- yuzhewu207/EYBX33PLACE2Unclearunknown102 downloads in 30 days
- RegalFire/GameAgent-Horizon-120KPermissive or share-alikemit101 downloads in 30 days
- tryforge/cad-1000-dpoPermissive or share-alikecc-by-sa-4.0101 downloads in 30 days
- FirespawnStudios/null-epoch-season-0Use restrictionscc-by-nc-4.0100 downloads in 30 days
- cameronangliss/vgc-battle-logs-svPermissive or share-alikemit100 downloads in 30 days
- novastar112/pusht_96_int1_visual_nomarker_allstep_thinking_trickiness_cotUnclearother100 downloads in 30 days
- webxos/arachnid_RLPermissive or share-alikemit100 downloads in 30 days
- jatshi/trusted-full-duplex-agent-dataPermissive or share-alikeapache-2.099 downloads in 30 days
- vibrantlabsai/pool-desk-v8Permissive or share-alikecc0-1.099 downloads in 30 days
- zhangdw/minigridPermissive or share-alikemit99 downloads in 30 days
- allenai/Dolci-RL-Zero-General-7BPermissive or share-alikeodc-by98 downloads in 30 days
- fblgit/simple-math-DPOUse restrictionscc-by-nc-nd-4.098 downloads in 30 days
- rmems/agent-trajectory-preference-pairsPermissive or share-alikeapache-2.098 downloads in 30 days
- Attoloop/club-mixPermissive or share-alikeapache-2.097 downloads in 30 days
- cmunley/mixed-skills-envPermissive or share-alikeapache-2.097 downloads in 30 days
- gittensor-model-hub/cuda-nsys-trainingPermissive or share-alikemit96 downloads in 30 days
- atrost/tmax-nemo-v09-variable-pass-no-git-pager-recoveryPermissive or share-alikeodc-by95 downloads in 30 days
- cedricable/evidence-triage-labPermissive or share-alikemit95 downloads in 30 days
- eagle0504/multireward-grpo-gsm8k-rewards-qwen2.5-7bPermissive or share-alikecc-by-4.095 downloads in 30 days
- neuralcrystal/checkers-positionsPermissive or share-alikecc-by-4.095 downloads in 30 days
- violetxi/tb2-eval-qwen3-8b-wm-summary-mixed-source-v2-16gPermissive or share-alikeapache-2.095 downloads in 30 days
- DeepNLP/AI-Agent-Marketplace-IndexPermissive or share-alikemit94 downloads in 30 days
- leohink/assistax-zooPermissive or share-alikeapache-2.094 downloads in 30 days
- ryangowe/ets2-datasetUnclearother94 downloads in 30 days
- tergite/tergite-chipcalPermissive or share-alikeapache-2.094 downloads in 30 days
- HuberyLL/nms_hitl_world_modelPermissive or share-alikecc0-1.093 downloads in 30 days
- haidang2405/seqevalbench-exact-propensity-logged-tracesPermissive or share-alikecc-by-4.093 downloads in 30 days
- oolongie/colorful-maze-trajectoriesPermissive or share-alikemit93 downloads in 30 days
- open-athena/nemotron-gym-knowledge-openqaPermissive or share-alikecc-by-4.093 downloads in 30 days
- wwwenlin/skillscaffold-tau-rlPermissive or share-alikeapache-2.093 downloads in 30 days
- LisaMegaWatts/sshfighter-17-head-router-v1Permissive or share-alikemit92 downloads in 30 days
- LisaMegaWatts/sshfighter-policy-fusion-v1Permissive or share-alikemit92 downloads in 30 days
- Syndicate604/evidence-deskPermissive or share-alikeapache-2.092 downloads in 30 days
- homerquan/boardgamebench-answer-sftPermissive or share-alikeapache-2.092 downloads in 30 days
- jasonyandell/texas-42-lem-pour-aPermissive or share-alikecc0-1.092 downloads in 30 days
- lance-format/gaming-500-hours-lanceUnclearother92 downloads in 30 days
- mj0530/CERA-MoA-trainUnclearother92 downloads in 30 days
- tergite/tergite-chipcal-runsPermissive or share-alikeapache-2.092 downloads in 30 days
- AdamAtractor/btc-l2-orderbookPermissive or share-alikecc-by-4.091 downloads in 30 days
- ishagarg1103/cua-benchPermissive or share-alikecc-by-4.091 downloads in 30 days
- muretai/network-episodesUnclearother91 downloads in 30 days
- AndrewThompson1233/Chess-Alpha-700KPermissive or share-alikeapache-2.090 downloads in 30 days
- Deterministic-Data/deterministic-trajectory-transitions-25kUnclearother90 downloads in 30 days
- cyberjanitor/hermes-session-digestsPermissive or share-alikemit90 downloads in 30 days
- LisaMegaWatts/sshfighter-17-head-router-ack-sticky-v1Permissive or share-alikemit89 downloads in 30 days
- Nobody05/arc-agi3-codex-gpt5.6sol-g50tPermissive or share-alikecc-by-4.089 downloads in 30 days
- open-athena/nemotron-gym-reasoning-gym-v2Permissive or share-alikecc-by-4.089 downloads in 30 days
- vibrantlabsai/pool-desk-v5Possible licence conflictother89 downloads in 30 days
- AgentNativeResearchLab/arc-agi3-agy-kimi2.7-thinking-tr87Permissive or share-alikecc-by-4.088 downloads in 30 days
- cmunley/mixed-skills-env-v13Permissive or share-alikeapache-2.088 downloads in 30 days
- vibrantlabsai/pool-desk-v7Possible licence conflictother88 downloads in 30 days
- haosulab/ManiSkill_PlugChargerPermissive or share-alikeapache-2.087 downloads in 30 days
- zhiyuanhucs/marvels-spider-man-2-bcUnclearother87 downloads in 30 days
- Autobrik/teaching-cartpole-10k-v1Permissive or share-alikemit86 downloads in 30 days
- JWei05/swe_smith_rebenchv2_5136Unclearother86 downloads in 30 days
- masonhargrave/epicarePermissive or share-alikeunlicense86 downloads in 30 days
- Archangel-system/helpsteer2-preference-openai-nativePermissive or share-alikecc-by-4.085 downloads in 30 days
- LisaMegaWatts/sshfighter-policy-fusion-leg3Permissive or share-alikemit85 downloads in 30 days
- Sraghvi/dual-arm-robot-datasetPermissive or share-alikemit85 downloads in 30 days
- WithinUsAI/OpenToolTrace-XPermissive or share-alikeapache-2.085 downloads in 30 days
- haosulab/ManiSkill_StackCubePermissive or share-alikeapache-2.085 downloads in 30 days
- jwjeonn/smacv2-offlinePermissive or share-alikecc-by-4.085 downloads in 30 days
- leokk/RL-100-adroit-door-mediumUnclearother85 downloads in 30 days
- mohamed12ahmed/AgentForge-BenchPermissive or share-alikemit85 downloads in 30 days
- nagisanzeninz/Nagi-Machine-ZooPermissive or share-alikecc-by-4.085 downloads in 30 days
- open-athena/nemotron-gym-safetyPermissive or share-alikecc-by-4.085 downloads in 30 days
- Nanthasit/hermes-tool-use-rl-envPermissive or share-alikecc-by-4.084 downloads in 30 days
- RKB109/contextual-bandit-simulator-20261003-datasetPermissive or share-alikecc-by-4.084 downloads in 30 days
- chz05/rollout_tracePermissive or share-alikemit84 downloads in 30 days
- webxos/snipercell_RLPermissive or share-alikemit84 downloads in 30 days
- webxos/wavebender_datasetPermissive or share-alikemit84 downloads in 30 days
- LisaMegaWatts/sshfighter-policy-fusion-leg2Permissive or share-alikemit83 downloads in 30 days
- NLPLab-SoICT/Vi-SRSPermissive or share-alikeapache-2.083 downloads in 30 days
- cmunley/mixed-skills-env-v2bPermissive or share-alikeapache-2.083 downloads in 30 days
- haidang2405/senseshift-rl-real-world-active-sensingPermissive or share-alikecc-by-4.083 downloads in 30 days
- BRADY99/rl-game-traces-elden-ringUnclearother82 downloads in 30 days
- Hao13911949273/MinusData-Chem-Negative-PoCPermissive or share-alikecc-by-4.082 downloads in 30 days
- cmunley/mixed-skills-env-v8Permissive or share-alikeapache-2.082 downloads in 30 days
- data-is-better-together/aya_dutch_dpoPermissive or share-alikeapache-2.082 downloads in 30 days
- kanishqgandharv/olsd-v0.1Permissive or share-alikeapache-2.082 downloads in 30 days
- zhangdw/sokobanPermissive or share-alikeapache-2.082 downloads in 30 days
- Nabidnur/arc-agi-3-verified-playbooksPermissive or share-alikeapache-2.081 downloads in 30 days
- PetraAI/Microsoft_LearnPermissive or share-alikemit81 downloads in 30 days
- lkevincc0/playtracePermissive or share-alikeapache-2.081 downloads in 30 days
- luca0621/appgen-ued-v32r12-training-dataUnclearother81 downloads in 30 days
- webxos/drone_fsd_datasetPermissive or share-alikemit81 downloads in 30 days
- Rihong/bird-rlPermissive or share-alikeapache-2.080 downloads in 30 days
- chenbhao/Versper-V1-Evo-ORPO-GPT5.5-Think-Recursive-25kPermissive or share-alikeapache-2.080 downloads in 30 days
- johnstrilians/Recraft-V2_t2i_human_preferenceUnclearcdla-permissive-2.080 downloads in 30 days
- kshitijthakkar/pramaan-proof-of-art-openenvPermissive or share-alikecc-by-4.080 downloads in 30 days
- martincousseau/refund-arenaPermissive or share-alikeapache-2.080 downloads in 30 days
- nyuuzyou/casino-benchmarkUnclearother80 downloads in 30 days
- pranavvmurthy26/synthetic-healthcare-tool-calling-grpo-rlvr-1kPermissive or share-alikeapache-2.080 downloads in 30 days
- cmunley/mixed-skills-env-v3Permissive or share-alikeapache-2.079 downloads in 30 days
- AmanPriyanshu/Recursive-Task-Synthesis-CopyPermissive or share-alikecc-by-4.078 downloads in 30 days
- RKB109/contextual-bandit-simulator-20261013-datasetPermissive or share-alikecc-by-4.078 downloads in 30 days
- Sami2305341176/JudgmentBenchPermissive or share-alikemit78 downloads in 30 days
- ZhiyuanZhangZhiyuan/ContactWorldUnclearother78 downloads in 30 days
- clawLooop/clawloop-dataPermissive or share-alikemit78 downloads in 30 days
- cmunley/mixed-skills-env-v6Permissive or share-alikeapache-2.078 downloads in 30 days
- Kaszanas/SC2ReSetUnclearother77 downloads in 30 days
- Trofish/Korean-RLHF-Full-processUse restrictionscc-by-nc-4.077 downloads in 30 days
- WootzappLab/cua-benchPermissive or share-alikecc-by-4.077 downloads in 30 days
- chrisxx/doom-2players-latentsPermissive or share-alikemit77 downloads in 30 days
- jcformanek/moltenpotPermissive or share-alikeapache-2.077 downloads in 30 days
- lxy222222/RobotLab-G1-MultiDynamics-official-mixed-v1Unclearother77 downloads in 30 days
- SH11235/tanuki-2024-07-30-1-qsearch-suisho5Permissive or share-alikemit76 downloads in 30 days
- cmunley/mixed-skills-env-v4Permissive or share-alikeapache-2.076 downloads in 30 days
- penji2803/turtlebot3-moving-obstacles-lidar-1.5mPermissive or share-alikecc-by-4.076 downloads in 30 days
- DBbun/Mixed-Initiative-Lookout-CHI99Permissive or share-alikeapache-2.075 downloads in 30 days
- OpceanAI/sota-mathPermissive or share-alikemit75 downloads in 30 days
- RaTan23/jarvis-reasoning-dpoPermissive or share-alikeapache-2.075 downloads in 30 days
- quastAI/ogbench-cube-quadruple-domain-randomized-expertPermissive or share-alikemit75 downloads in 30 days
- Xnhyacinth/codegenUnclearother74 downloads in 30 days
- charithmunasinghe/piper_picking_testsPermissive or share-alikemit74 downloads in 30 days
- novastar112/pusht_96_norm4_visual_nomarker_allstep_thinking_trickiness_cotUnclearother74 downloads in 30 days
- nuhmanpk/financial-literacy-instructPermissive or share-alikeapache-2.074 downloads in 30 days
- LisaMegaWatts/sshfighter-current-epoch-baseline-459Permissive or share-alikemit73 downloads in 30 days
- MaxPrestige/CRUDE_OIL_PRICESPermissive or share-alikeapache-2.073 downloads in 30 days
- aditya-shriwastava/autouxPermissive or share-alikemit73 downloads in 30 days
- eduagentbench/eduagentbenchUse restrictionscc-by-nc-sa-4.073 downloads in 30 days
- forseasons/autoterminalworld-tb3-selected-five-v4-finalUnclearother73 downloads in 30 days
- msr-spare-1/spare-gpt55-static-corpusPermissive or share-alikeapache-2.073 downloads in 30 days
- renhuimin/RL-Instruction-Following-DatasetPermissive or share-alikeapache-2.073 downloads in 30 days
- taso-labs/strategybenchPermissive or share-alikecc-by-4.073 downloads in 30 days
- wwbrannon/twinviews-13kPermissive or share-alikecc-by-4.073 downloads in 30 days
- xiaoluo11/dyson-sphere-program-gameplay-dataUnclearother73 downloads in 30 days
- OstensibleParadox/recursive-linesPossible licence conflictcc-by-nc-4.072 downloads in 30 days
- RKB109/contextual-bandit-simulator-20261023-datasetPermissive or share-alikecc-by-4.072 downloads in 30 days
- arvindcr4/tinker-rl-bench-wandbPermissive or share-alikeapache-2.072 downloads in 30 days
- dannyobito/arena-poker-reasoned-decisions-v0Permissive or share-alikecc-by-4.072 downloads in 30 days
- kshitijthakkar/arena-all8-v32-field-rewardPermissive or share-alikemit72 downloads in 30 days
- webxos/nexus-fpvPermissive or share-alikemit72 downloads in 30 days
- Archangel-system/oasst2-openai-nativePermissive or share-alikeapache-2.071 downloads in 30 days
- NathanGavenski/Labyrinth-v0_5x5Permissive or share-alikemit71 downloads in 30 days
- True2456/code-as-actionPermissive or share-alikeapache-2.071 downloads in 30 days
- haosulab/ManiSkill_PushCubePermissive or share-alikeapache-2.071 downloads in 30 days
- nph4rd/eleusis-simple-rulesPermissive or share-alikemit71 downloads in 30 days
- 1rahu/mini-coffee-test-trajectoriesPermissive or share-alikemit70 downloads in 30 days
- Adilbai/stock-datasetPermissive or share-alikemit70 downloads in 30 days
- armaanp/gen9-random-doubles-replaysPermissive or share-alikemit70 downloads in 30 days
- ob11/VL-PRM300KPermissive or share-alikeapache-2.070 downloads in 30 days