mlsanityData to 7 Oct 2026

HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation

arXiv 2403.10506 ↗First posted 15 Mar 2024cs.RO cs.AI cs.LGcited by 101

Not on the map. Why?

Abstract (arXiv)

Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology. However, research in humanoid robots is often bottlenecked by the costly and fragile hardware setups. To accelerate algorithmic research in humanoid robots, we present a high-dimensional, simulated robot learning benchmark, HumanoidBench, featuring a humanoid robot equipped with dexterous hands and a variety of challenging whole-body manipulation and locomotion tasks. Our findings reveal that state-of-the-art reinforcement learning algorithms struggle with most tasks, whereas a hierarchical learning approach achieves superior performance when supported by robust low-level policies, such as walking or reaching. With HumanoidBench, we provide the robotics community with a platform to identify the challenges arising when solving diverse tasks with humanoid robots, facilitating prompt verification of algorithms and ideas. The open-source code is available at https://humanoid-bench.github.io.

Key facts. Cited by 101 papers in the map (data through 7 Oct 2026). Builds on 47 of its 69 references that are in the map. First posted on arXiv 15 Mar 2024.

Builds on

47 of 69 references.

References · 47

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  4. 2016OpenAI Gymcited by 1,684
  5. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  6. 2023Mastering Diverse Domains through World Modelscited by 1,193
  7. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  8. 2018DeepMind Control Suitecited by 935
  9. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  10. 2019Solving Rubik's Cube with a Robot Handcited by 699
  11. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  12. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
35 more
  1. 2018Learning Dexterous In-Hand Manipulationcited by 643
  2. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  3. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 501
  4. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  5. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  6. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 436
  7. 2016The Option-Critic Architecturecited by 433
  8. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  9. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  10. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 380
  11. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  12. 2020dm_control: Software and Tasks for Continuous Controlcited by 368
  13. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
  14. 2017One-Shot Imitation Learningcited by 232
  15. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 220
  16. 2021BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environmentscited by 161
  17. 2023FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulationcited by 132
  18. 2020SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulationcited by 118
  19. 2024Expressive Whole-Body Control for Humanoid Robotscited by 117
  20. 2023Robot Parkour Learningcited by 115
  21. 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 111
  22. 2022Discovered Policy Optimisationcited by 103
  23. 2022MyoSuite -- A contact-rich simulation suite for musculoskeletal motor controlcited by 80
  24. 2023PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interactioncited by 72
  25. 2019IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Taskscited by 68
  26. 2022Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Searchcited by 61
  27. 2023Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensingcited by 51
  28. 2022Factory: Fast Contact for Robotic Assemblycited by 49
  29. 2023Hierarchical Planning and Control for Box Loco-Manipulationcited by 42
  30. 2023LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotioncited by 31
  31. 2023The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learningcited by 24
  32. 2023MyoDex: A Generalizable Prior for Dexterous Manipulationcited by 11
  33. 2020Sim-to-real for high-resolution optical tactile sensing: From images to 3D contact force distributionscited by 6
  34. 2023Exploring Kinodynamic Fabrics for Reactive Whole-Body Control of Underactuated Humanoid Robotscited by 5
  35. 2023MIMo: A Multi-Modal Infant Model for Studying Cognitive Developmentcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 45; 2026: 42.

101 papers.

Sort:

By area:

  1. 2025RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twinscited by 117
  2. 2024SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learningcited by 70
  3. 2024RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)cited by 68
  4. 2025InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactionscited by 67
  5. 2025WorldEval: World Model as Real-World Robot Policies Evaluatorcited by 64
  6. 2025Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Modelscited by 51
  7. 2026World Action Models: The Next Frontier in Embodied AIcited by 46
  8. 2025LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instructioncited by 40
  9. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  10. 2025Hyperspherical Normalization for Scalable Deep Reinforcement Learningcited by 35
  11. 2025ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learningcited by 34
  12. 2025Flow-Based Policy for Online Reinforcement Learningcited by 33
38 more
  1. 2025FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Controlcited by 32
  2. 2024BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmarkcited by 30
  3. 2024MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximizationcited by 30
  4. 2024SMPLOlympics: Sports Environments for Physically Simulated Humanoidscited by 29
  5. 2025RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluationcited by 29
  6. 2024Body Transformer: Leveraging Robot Embodiment for Policy Learningcited by 26
  7. 2024Hierarchical World Models as Visual Whole-Body Humanoid Controllerscited by 24
  8. 2025ManipBench: Benchmarking Vision-Language Models for Low-Level Robot Manipulationcited by 24
  9. 2025SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrationscited by 23
  10. 2025Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learnerscited by 23
  11. 2024ActSafe: Active Exploration with Safety Constraints for Reinforcement Learningcited by 22
  12. 2024A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approachescited by 19
  13. 2025XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learningcited by 17
  14. 2024Diffusing States and Matching Scores: A New Framework for Imitation Learningcited by 16
  15. 2024Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimickingcited by 14
  16. 2025Bootstrapped Model Predictive Controlcited by 13
  17. 2025H3DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learningcited by 13
  18. 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learningcited by 12
  19. 2025Towards Embodiment Scaling Laws in Robot Locomotioncited by 12
  20. 2025HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoningcited by 12
  21. 2025Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agentscited by 12
  22. 2024Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learningcited by 10
  23. 2025SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blendingcited by 9
  24. 2025Subtask-Aware Visual Reward Learning from Segmented Demonstrationscited by 7
  25. 2025TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Controlcited by 6
  26. 2025Bootstrap Off-policy with World Modelcited by 6
  27. 2025Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervisioncited by 5
  28. 2025DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Expertscited by 5
  29. 2025Compute-Optimal Scaling for Value-Based Deep RLcited by 5
  30. 2026The Surprising Difficulty of Search in Model-Based Reinforcement Learningcited by 5
  31. 2026FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matchingcited by 5
  32. 2026FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Controlcited by 5
  33. 2025D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentationcited by 4
  34. 2025Sari Sandbox: A Virtual Retail Store Environment for Embodied AI Agentscited by 4
  35. 2025Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraintscited by 4
  36. 2026Scalable Exploration for High-Dimensional Continuous Control via Value-Guided Flowcited by 4
  37. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 4
  38. 2024λ: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Roboticscited by 3

50 most cited of 101 All 101 (JSON)