Task: reinforcement-learning
1,403 datasets. Listed here: 1,276 of them, most downloaded first. Page 7 of 7.
- dhruvrajpal/defense-logistics-stochastic-simulationUse restrictionscc-by-nc-4.021 downloads in 30 days
- eagle0504/warren-buffett-letters-qna-r1-enhanced-1998-2024Permissive or share-alikemit21 downloads in 30 days
- markuspomm/r-omega-frameworkPermissive or share-alikecc-by-4.021 downloads in 30 days
- noidvan/jaipurUse restrictionscc-by-nc-4.021 downloads in 30 days
- solsticestudioai/arc-t-defi-packPermissive or share-alikecc-by-4.021 downloads in 30 days
- sungyub/guru-logic-verlPermissive or share-alikeapache-2.021 downloads in 30 days
- violetxi/tb2-eval-qwen35-4b-basePermissive or share-alikeapache-2.021 downloads in 30 days
- Datoric/action-conditioned-gameplay-10000hUnclearother20 downloads in 30 days
- NathanGavenski/Ant-v2Permissive or share-alikemit20 downloads in 30 days
- kimic/pitfallPermissive or share-alikemit20 downloads in 30 days
- mattismegevand/bloxorzPermissive or share-alikemit20 downloads in 30 days
- novastar112/sokoban_hard_remap_allstep_thinking_trickiness_cotUnclearother20 downloads in 30 days
- sam-dude/go1-expert-trajectoriesPermissive or share-alikemit20 downloads in 30 days
- violetxi/tb2-eval-qwen35-4b-wm-summaryPermissive or share-alikeapache-2.020 downloads in 30 days
- vshwanilgv/wenavigatecontroller-long-episodesPermissive or share-alikemit20 downloads in 30 days
- yashppawar/permit-pathfinder-trajectoriesPermissive or share-alikebsd-3-clause20 downloads in 30 days
- ClarusC64/clarus_alignment_flip_test_v01Unclearother19 downloads in 30 days
- NagaYu/groundhog-world-tapesPermissive or share-alikeapache-2.019 downloads in 30 days
- PolarAI/Aegis-Safety-DPOPermissive or share-alikegpl-3.019 downloads in 30 days
- augustus2011/cpdc2025-dialogue-reasoning-genPermissive or share-alikeapache-2.019 downloads in 30 days
- bengusu80/humanoid-joint-control-datasetPermissive or share-alikemit19 downloads in 30 days
- cloudronin/vetoworld-occasion-logPermissive or share-alikemit19 downloads in 30 days
- jonhlin/stg-rl-train-envsPermissive or share-alikeapache-2.019 downloads in 30 days
- novastar112/toy_maze_2d_train_allstep_thinking_future_rollout_cot_with_distanceUnclearother19 downloads in 30 days
- play0718/Replica-Shared-Context-v2Unclearother19 downloads in 30 days
- spy5er/Gemma4-NPC-DatasetUse restrictionscc-by-nc-sa-4.019 downloads in 30 days
- ultrastar111/sokoban_easy_v8_noncot_chunk_k1_world_model_20260622_persegUse restrictionscc-by-nc-4.019 downloads in 30 days
- zhiyuanhucs/vpn-upload-test-videoUnclearother19 downloads in 30 days
- ClarusC64/deceptive_helpfulness_boundary_v01Unclearother18 downloads in 30 days
- CultriX/aya_dutch_dpo_binarizedPermissive or share-alikeapache-2.018 downloads in 30 days
- GoldenGrapeGentleman1/battle-game-grpo-tutorialPermissive or share-alikemit18 downloads in 30 days
- bengusu80/humanoid-imu-balance-datasetPermissive or share-alikeapache-2.018 downloads in 30 days
- brysgo/gol-rl-diversified-38074946Permissive or share-alikemit18 downloads in 30 days
- dmnsh/caliber-extension-gemma4-e2b-grpo-rolloutsPermissive or share-alikeapache-2.018 downloads in 30 days
- jackvandervall/rottermaatje-synthetic-corpusPermissive or share-alikeapache-2.018 downloads in 30 days
- kuririrn/alfworld_roundwise_dpo_v1Unclearother18 downloads in 30 days
- sheng22213/pku-safe-rlhf-masked-arm-round4-extreme-v2-trainingUnclearother18 downloads in 30 days
- ultrastar111/sokoban_easy_v8_cot_chunk_k3_world_model_20260622_persegUse restrictionscc-by-nc-4.018 downloads in 30 days
- Amanpatel81/my_smolvla123456789Permissive or share-alikeapache-2.017 downloads in 30 days
- AntimLabs/combined-game-sftPermissive or share-alikemit17 downloads in 30 days
- Audioset/HANDPAN-AI-DATASETUnclearno licence declared17 downloads in 30 days
- ClarusC64/ai-reward-channel-attack-surface-coherence-collapse-v0.1Permissive or share-alikemit17 downloads in 30 days
- Datoric/robot-teleoperation-2000-episodesUnclearother17 downloads in 30 days
- Eyght/GRPO-Reasoning-Tools-CleanedPermissive or share-alikemit17 downloads in 30 days
- Goyoonjung/my-robotics-dataset-12Permissive or share-alikemit17 downloads in 30 days
- LKForge/negamax-search-depth-scalingPermissive or share-alikemit17 downloads in 30 days
- THULab/qcea_adaptive_agent_benchmarkPermissive or share-alikemit17 downloads in 30 days
- ambrosfitz/yawp_thinkingPermissive or share-alikemit17 downloads in 30 days
- hheric/WTIUnclearother17 downloads in 30 days
- mobileforge-anonymous/mobileforge-benchmark-resultsPermissive or share-alikeapache-2.017 downloads in 30 days
- novastar112/toy_maze_2d_easy_allstep_thinking_future_rollout_cot_500kUnclearother17 downloads in 30 days
- seil-umd/STL-ParkourPermissive or share-alikecc-by-4.017 downloads in 30 days
- ultrastar111/sokoban_hard_v8_init_state_pool_20260711Use restrictionscc-by-nc-4.017 downloads in 30 days
- victor203/fitness-preferencesPermissive or share-alikemit17 downloads in 30 days
- CALM-Dataset/CALM-GermanyPermissive or share-alikecc-by-4.016 downloads in 30 days
- Mahesh111000/Hanabi_datasetPermissive or share-alikemit16 downloads in 30 days
- ParamTatva/mujoco-sota-benchmarkPermissive or share-alikeapache-2.016 downloads in 30 days
- TokenBender/dummy-pie-cpp-oracle-seedPermissive or share-alikemit16 downloads in 30 days
- TommyShen/Factor-FB-OfflinePermissive or share-alikemit16 downloads in 30 days
- abdessamad-bourkibate/TVO-Laminar-Family-AlignmentPermissive or share-alikeapache-2.016 downloads in 30 days
- anonymoususermargin/ercot-rtcb-v1Permissive or share-alikemit16 downloads in 30 days
- debaterhub/ipda-phase5-v2Permissive or share-alikeapache-2.016 downloads in 30 days
- devsgnr/bio-safety-peft-loraPermissive or share-alikemit16 downloads in 30 days
- hellojais/billiards-worldmodelPermissive or share-alikemit16 downloads in 30 days
- kattri15/actionshiftPermissive or share-alikemit16 downloads in 30 days
- kaus4004/robust-humanoid-ppo-resultsPermissive or share-alikemit16 downloads in 30 days
- novastar112/sokoban_easy_remap_allstep_thinking_trickiness_cotUnclearother16 downloads in 30 days
- novastar112/toy_maze_2d_hard_allstep_thinking_future_rollout_cot_500kUnclearother16 downloads in 30 days
- sungyub/docqa-rl-verlPermissive or share-alikeapache-2.016 downloads in 30 days
- Rendra86318/robot_demos_with_state_resetPermissive or share-alikemit15 downloads in 30 days
- beersrobert/RW-LVTPermissive or share-alikecc-by-4.015 downloads in 30 days
- kimic/pacmanPermissive or share-alikemit15 downloads in 30 days
- mhieuuu/ac-solver-datasetPermissive or share-alikemit15 downloads in 30 days
- radiuson/drone-testPermissive or share-alikemit15 downloads in 30 days
- novastar112/visgym_pacman_2d_randomUnclearother13 downloads in 30 days
- novastar111/pacman_v0_remapUnclearother8 downloads in 30 days