{"url":"/dataset/rlbench","name":"RLBench","full_name":null,"description_markdown":"**RLBench** is an ambitious large-scale benchmark and learning environment designed to facilitate research in a number of vision-guided manipulation research areas, including: reinforcement learning, imitation learning, multi-task learning, geometric computer vision, and in particular, few-shot learning.","description_withheld":null,"homepage":"https://sites.google.com/view/rlb","introduced_date":"2019-09-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/rlbench-the-robot-learning-benchmark-learning","title":"RLBench: The Robot Learning Benchmark & Learning Environment","first_author":"Stephen James","url":null},"license":{"name":"Custom (non-commercial)","url":"https://github.com/stepjam/RLBench/blob/master/LICENSE"},"modalities":[{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[{"name":"Robot Manipulation","url":"/task/robot-manipulation","datasets_with_task":"/datasets/task/robot-manipulation"},{"name":"Robot Manipulation Generalization","url":"/task/robot-manipulation-generalization","datasets_with_task":"/datasets/task/robot-manipulation-generalization"},{"name":"Imitation Learning","url":"/task/imitation-learning","datasets_with_task":"/datasets/task/imitation-learning"}],"languages":[],"variants":["RLBench","The COLOSSEUM","GEMBench"],"data_loaders":[],"num_papers_in_archive":167,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/robot-manipulation-on-rlbench","task":"Robot Manipulation","dataset_variant":"RLBench","rows":18,"metrics":["Succ. Rate (18 tasks, 100 demo/task)","Succ. Rate (18 tasks, 10 demo/task)","Training Time (V100 x 8 x day)","Training Time (A100 x hour)","Succ. Rate (10 tasks, 100 demos/task)","Succ. Rate (74 tasks, 100 demos/task)","Inference Speed (fps)","Input Image Size"],"first_row_in_archive_order":{"model":"EquAct","paper":null,"metrics":{"Inference Speed (fps)":"1.4","Input Image Size":"256","Succ. Rate (18 tasks, 10 demo/task)":"60.1","Succ. Rate (18 tasks, 100 demo/task)":"89.4","Training Time (A100 x hour)":"240"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/robot-manipulation-generalization-on-gembench","task":"Robot Manipulation Generalization","dataset_variant":"GEMBench","rows":6,"metrics":["Average Success Rate","Average Success Rate (L1)","Average Success Rate (L2)","Average Success Rate (L3)","Average Success Rate (L4)"],"first_row_in_archive_order":{"model":"3D-LOTUS++","paper":"/paper/towards-generalizable-vision-language-robotic","metrics":{"Average Success Rate":"48.0","Average Success Rate (L1)":"68.7±0.6","Average Success Rate (L2)":"64.5±0.9","Average Success Rate (L3)":"41.5±1.8","Average Success Rate (L4)":"17.4±0.4"},"code_links":[{"title":"vlc-robot/robot-3dlotus","url":"https://github.com/vlc-robot/robot-3dlotus"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/train-a-multi-task-diffusion-policy-on","title":"Mini Diffuser: Fast Multi-task Diffusion Policy Training Using Two-level Mini-batches","date":"2025-05-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/autoregressive-action-sequence-learning-for","title":"Autoregressive Action Sequence Learning for Robotic Manipulation","date":"2024-10-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":13,"samples_unverified":1,"pointer_only_for_licence":14,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/towards-generalizable-vision-language-robotic","title":"Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy","date":"2024-10-02","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rvt-2-learning-precise-manipulation-from-few","title":"RVT-2: Learning Precise Manipulation from Few Demonstrations","date":"2024-06-12","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":15,"samples_unverified":0,"pointer_only_for_licence":15,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sam-e-leveraging-visual-foundation-model-with","title":"SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation","date":"2024-05-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/3d-diffuser-actor-policy-diffusion-with-3d","title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","date":"2024-02-18","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/polarnet-3d-point-clouds-for-language-guided","title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","date":"2023-09-27","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/act3d-infinite-resolution-action-detection","title":"Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation","date":"2023-06-30","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/rvt-robotic-view-transformer-for-3d-object","title":"RVT: Robotic View Transformer for 3D Object Manipulation","date":"2023-06-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/perceiver-actor-a-multi-task-transformer-for","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","date":"2022-09-12","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/instruction-driven-history-aware-policies-for","title":"Instruction-driven history-aware policies for robotic manipulations","date":"2022-09-11","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/auto-lambda-disentangling-dynamic-task","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","date":"2022-02-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-q-attention-efficient-learning","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","date":"2021-06-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sam2act-integrating-visual-foundation-model-1","title":"SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation","date":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":43,"samples_ran":30,"samples_unverified":13,"pointer_only_for_licence":30,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}