REVIEW 35 cited by
HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 35 Pith papers
-
Labimus: A Simulation and Benchmark for Humanoid Dexterous Manipulation in Chemical Laboratory
Labimus is the first benchmark for humanoid dexterous manipulation in organic chemistry laboratories, exposing a gap between task completion and required experimental precision.
-
HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning
HumanoidArena is a new benchmark of 7 leg-critical HOI/HSI tasks that evaluates egocentric hierarchical whole-body policies in humanoids and finds performance is strongly conditioned on the low-level GMT used.
-
Real-IKEA: Physical Fidelity is the Prerequisite for Robust Manipulation
Real-IKEA supplies 1,079 physically accurate articulated asset configurations from real IKEA parts together with resistance-calibrated simulation parameters that enable RL policies to discover robust hooking and lever...
-
Generative Actor-Critic with Soft Bridge Policies
SoftGAC defines a stochastic bridge from base to action latent that converts the MaxEnt objective into a tractable relative-entropy term reducible to control energy, achieving competitive returns with one-pass sampling.
-
BiCoord: A Bimanual Manipulation Benchmark towards Long-Horizon Spatial-Temporal Coordination
BiCoord is a new benchmark for long-horizon tightly coordinated bimanual manipulation that includes quantitative metrics and shows existing policies like DP, RDT, Pi0 and OpenVLA-OFT struggle on such tasks.
-
First Deployable Dynamic-CoM: A Unified Policy and Method-Agnostic Benchmark for Humanoid Single-Leg Balance
A support-relative dynamic capture-point observation, reconstructible without base linear velocity, lets a humanoid policy hold clean single-leg balance at 86/90 in simulation and deploy on a Unitree G1 without distillation.
-
WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning
WOLF-VLA combines optimal-control motion synthesis with multi-modal dataset construction to train VLAs that generate whole-body humanoid locomotion policies from natural-language instructions.
-
When Does Non-Uniform Replay Matter in Reinforcement Learning?
Non-uniform replay helps off-policy RL mainly at low replay volumes, high-entropy sampling matters even at similar recency, and Truncated Geometric replay offers a low-overhead practical solution.
-
SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
SPHERE applies a Parseval penalty to MoE policies in continual RL to maintain spectral plasticity, yielding 133% and 50% higher average success on MetaWorld and HumanoidBench versus unregularized MoE baselines.
-
SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
SPHERE applies a Parseval penalty derived from a Neural Tangent Kernel proxy for spectral plasticity to Mixture-of-Experts policies, raising average success rates by 133% on MetaWorld and 50% on HumanoidBench in conti...
-
dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model
A discrete diffusion model tokenizes multimodal robotic data and uses a progress token to predict future states and task completion for scalable policy evaluation.
-
Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot
The Weightlessness Mechanism lets humanoid robots imitate non-self-stabilizing motions by dynamically relaxing specific joints to exploit passive environmental contacts, generalizing from single demonstrations to vari...
-
Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot
A weightlessness mechanism enables humanoid robots to dynamically relax joints for stable, contact-rich motions across diverse environments without task-specific tuning.
-
Mean Flow Policy Optimization
Mean Flow Policy Optimization (MFPO) uses few-step flow-based models for RL policies and achieves performance on par with or better than diffusion-based methods while substantially lowering training and inference time...
-
Mean Flow Policy Optimization
MeanFlow policies optimized by soft policy iteration with an average-divergence network and adaptive SNIS velocity estimation match diffusion RL performance at far lower sampling cost.
-
FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.
-
FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
FlashSAC scales up Soft Actor-Critic with fewer updates, larger models, higher data throughput, and norm bounds to deliver faster, more stable training than PPO on high-dimensional robot control tasks across dozens of...
-
PHUMA: Physically Reliable Humanoid Locomotion Dataset
PHUMA is a curated 73-hour humanoid locomotion corpus whose physical-reliability metrics are partly defined by the same losses used to optimize it, and whose imitation success claims are confounded by in-distribution ...
-
Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning
MINTO sets bootstrapped targets to the minimum of online and target network estimates, yielding faster stable value learning across online/offline RL and discrete/continuous actions.
-
Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control
PEGrad projects energy-minimization gradients orthogonal to task-reward gradients in RL, achieving 64% torque reduction in simulation and reduced battery draw on a Unitree Go2 without sacrificing task reward.
-
Sari Sandbox: A Virtual Retail Store Environment for Embodied AI Agents
A photorealistic Unity-based retail store environment with 250 items, a Python API, and a VR human-demonstration benchmark for embodied AI shopping agents.
-
Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
The paper introduces MTBench, a GPU-accelerated benchmark for massively parallel multi-task RL, and reports experiments suggesting on-policy methods outperform off-policy baselines while value learning limits MTRL per...
-
WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning
WOLF-VLA creates a dataset of optimal-control humanoid trajectories and trains a VLA model to generate locomotion policies from natural language instructions, with planned open release of data and tools.
-
DeepInsight: A Unified Evaluation Infrastructure Across the Physical AI Stack
DeepInsight introduces a unified evaluation infrastructure for the full Physical AI stack using three invariant abstractions to enable cross-layer diagnostics on one runtime.
-
Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning
Marope applies hierarchical MARL with decentralized lower-level rope policies and a centralized scheduler to achieve cooperative long rope skipping on Unitree G1 humanoids in simulation and reality.
-
When Does Non-Uniform Replay Matter in Reinforcement Learning?
Non-uniform replay improves RL sample efficiency mainly in low replay-volume regimes, with high-entropy sampling being key even at comparable recency.
-
When Does Non-Uniform Replay Matter in Reinforcement Learning?
Non-uniform replay helps most when replay volume is low; high-entropy sampling remains important, and a truncated geometric distribution delivers better sample efficiency with negligible overhead.
-
ALAS: Adaptive Long-Horizon Action Synthesis via Async-pathway Stream Disentanglement
ALAS disentangles environment and self-state streams via bio-inspired modules to deliver 23% higher subtask success and 29% better execution efficiency on long-horizon HSI tasks.
-
Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems
PRISM-WM uses a context-aware MoE with latent orthogonalization to model hybrid dynamics and reduce rollout drift for model-based planning.
-
Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents
Simplicial embeddings — group-wise softmax feature layers — improve sample efficiency and final performance of FastTD3, FastSAC, and PPO across continuous- and discrete-control benchmarks at no meaningful runtime cost.
-
GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation
GBC unifies MoCap retargeting and imitation learning into one framework that trains whole-body humanoid policies across multiple robot morphologies in simulation.
-
A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control
Forget and Grow (FoG) combines decaying replay weights for old experiences with progressive critic-network expansion to improve continuous-control reinforcement learning, beating BRO, SimBa, and TD-MPC2 on most of 41 ...
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
-
Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies
A survey that categorizes deep reinforcement learning scaling strategies into data, network, and training budget dimensions and outlines challenges for scaling DRL systems.
-
A Survey of Legged Robotics in Non-Inertial Environments: Past, Present, and Future
A literature survey summarizing modeling, state estimation, control methods, applications, and open challenges for legged robots operating in non-inertial environments where the ground moves or accelerates.
Discussion (0). Sign in to comment.