Pith. sign in

REVIEW 32 cited by

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

arxiv 2502.08844 v1 pith:F5WE4AWY submitted 2025-02-12 cs.RO

MuJoCo Playground

classification cs.RO
keywords playgroundmujocoframeworkroboticsim-to-realtrainingtransferachieved
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce MuJoCo Playground, a fully open-source framework for robot learning built with MJX, with the express goal of streamlining simulation, training, and sim-to-real transfer onto robots. With a simple "pip install playground", researchers can train policies in minutes on a single GPU. Playground supports diverse robotic platforms, including quadrupeds, humanoids, dexterous hands, and robotic arms, enabling zero-shot sim-to-real transfer from both state and pixel inputs. This is achieved through an integrated stack comprising a physics engine, batch renderer, and training environments. Along with video results, the entire framework is freely available at playground.mujoco.org

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 32 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Embedding Hybrid Systems into Continuous Latent Vector Fields

    cs.LG 2026-06 unverdicted novelty 7.0

    An n-dimensional hybrid system embeds into a continuous vector field in m > 2n dimensions, enabling latent Neural ODEs with consistency losses to recover hybrid flows from time series.

  2. ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders

    cs.RO 2026-05 unverdicted novelty 7.0

    ARC-RL provides four new MuJoCo continuous-control environments with hexapod and quadruped morphologies inspired by ARC Raiders, a unified multi-component reward without motion capture, CPG expert demonstrators, and e...

  3. asRoBallet: Closing the Sim2Real Gap via Friction-Aware Reinforcement Learning for Underactuated Spherical Dynamics

    cs.RO 2026-04 unverdicted novelty 7.0

    asRoBallet achieves the first hardware deployment of an end-to-end RL policy for a humanoid ballbot by training in a high-fidelity simulation that models discrete roller mechanics and multi-channel friction for zero-s...

  4. OrchardBench: A Physically-Grounded, GPU-Parallel Apple-Orchard Simulation Benchmark for Agricultural Robotics

    cs.RO 2026-07 conditional novelty 6.0

    OrchardBench simulates physically-grounded, breakable, fruit-bearing apple trees on a GPU-parallel engine to benchmark autonomous harvesting robots.

  5. CRAX: Fast Safe Reinforcement Learning Benchmarking

    cs.LG 2026-06 unverdicted novelty 6.0

    CRAX is a new fast benchmark suite for constrained RL built on MJX, with six environment suites and tasks across difficulty levels, showing no single safe RL method dominates and benefits from curriculum learning.

  6. Simulating Robotic Locomotion in Sand: Resistive Force Theory in an Open-Source Physics Engine

    cs.RO 2026-06 unverdicted novelty 6.0

    Implementation of 3D Granular Resistive Force Theory in MuJoCo predicts hexapod robot walking distance and foot sinkage in sand within 20% of physical experiments.

  7. Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning

    cs.RO 2026-06 unverdicted novelty 6.0

    Real2Sim tactile calibration, layout-aware encoder pretraining, and diffusion policy aggregation from object-specific RL experts enable 27% real-world success in blind grasping on a LEAP Hand for 10 seen and 10 unseen...

  8. MineXplore: An Open-Source Reinforcement Learning Exploration Benchmark for GNSS-Denied Underground Environment

    cs.RO 2026-06 unverdicted novelty 6.0

    MineXplore provides a MuJoCo-based underground mine navigation benchmark derived from real data, with geometric validation (IoU 0.9538) and a PPO baseline reaching 88.89% coverage.

  9. Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning

    cs.RO 2026-05 conditional novelty 6.0

    BARD is a self-contained PyTorch implementation of Featherstone's rigid body dynamics optimized for batched GPU evaluation and differentiation, reporting up to 64x throughput gains over Pinocchio on robot models with ...

  10. UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

    cs.RO 2026-05 unverdicted novelty 6.0

    UniLab is a CPU/GPU heterogeneous system for robot RL training using MuJoCoUni and MotrixSim backends that reports 3-10x end-to-end efficiency improvements and cross-platform compatibility beyond CUDA.

  11. ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders

    cs.RO 2026-05 accept novelty 6.0

    ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical c...

  12. GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning

    cs.RO 2026-04 unverdicted novelty 6.0

    GS-Playground delivers a high-throughput photorealistic simulator for vision-informed robot learning via parallel physics integrated with batch 3D Gaussian Splatting at 10^4 FPS and an automated Real2Sim workflow for ...

  13. asRoBallet: Closing the Sim2Real Gap via Friction-Aware Reinforcement Learning for Underactuated Spherical Dynamics

    cs.RO 2026-04 unverdicted novelty 6.0

    The paper presents the first successful zero-shot Sim2Real transfer of a friction-aware RL policy for a humanoid ballbot on physical hardware.

  14. A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies

    cs.RO 2026-04 unverdicted novelty 6.0

    Sim-and-real co-training for robot policies is driven primarily by balanced cross-domain representation alignment and secondarily by domain-dependent action reweighting.

  15. Simulation-Driven Evolutionary Motion Parameterization for Contact-Rich Granular Scooping with a Soft Conical Robotic Hand

    cs.RO 2026-04 unverdicted novelty 6.0

    A deformable soft conical hand is modeled in physics simulation and its scooping trajectories are optimized via evolutionary search, enabling effective contact-rich granular tasks validated in both simulation and phys...

  16. FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

    cs.LG 2026-04 unverdicted novelty 6.0

    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.

  17. FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

    cs.LG 2026-04 unverdicted novelty 6.0

    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...

  18. Learning Dexterous Grasping from Sparse Taxonomy Guidance

    cs.RO 2026-04 unverdicted novelty 6.0

    GRIT learns dexterous grasping from sparse taxonomy guidance, achieving 87.9% success and better generalization to novel objects via a two-stage prediction-plus-policy approach.

  19. FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control

    cs.LG 2026-03 unverdicted novelty 6.0

    FastDSAC enables state-of-the-art maximum entropy RL for high-dimensional humanoid control via entropy redistribution per dimension and improved continuous value estimation.

  20. PTLD: Sim-to-real Privileged Tactile Latent Distillation for Dexterous Manipulation

    cs.RO 2026-03 unverdicted novelty 6.0

    PTLD distills real privileged tactile data into a state estimator to boost sim-to-real performance of proprioceptive dexterous manipulation policies, yielding 182% improvement on in-hand rotation and 57% on reorientat...

  21. Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications

    cs.RO 2026-07 unverdicted novelty 5.0

    Framework using parameterized Signal Temporal Logic specifications to shape rewards for PPO-based RL, yielding tighter velocity tracking and more stable training than hand-crafted rewards on Barkour quadruped in MuJoC...

  22. Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering

    cs.RO 2026-06 unverdicted novelty 5.0

    MoRE improves robot policy success rates by 44 percentage points by distilling mode redirection into weights, matching filtered retraining performance without inference overhead.

  23. Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation

    cs.RO 2026-06 unverdicted novelty 5.0

    Joint velocity action space outperforms pose increment, pose velocity, and joint position increment for smoothness and performance in sim-to-real vision-based manipulation.

  24. QuadVerse: An Integrated Framework Aligning Visual-Physical Reality for Quadruped Simulation

    cs.RO 2026-06 unverdicted novelty 5.0

    QuadVerse integrates 3D Gaussian Splatting scene reconstruction, friction calibration via trajectory search, and a residual dynamics compensator to improve quadruped simulation fidelity and enable zero-shot policy transfer.

  25. Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion

    cs.RO 2026-05 unverdicted novelty 5.0

    Targeted changes to policy initialization, critic targets, and return estimation let SAC match PPO performance across legged locomotion tasks in massively parallel simulation.

  26. MuJoCoUni:Persistent Batched Runtime Primitives for MuJoCo

    cs.RO 2026-05 unverdicted novelty 5.0

    MuJoCoUni introduces BatchEnvPool, a C++/pybind11-based executor providing persistent batched stateful MuJoCo environments with domain randomization, sensor queries, and short stepping.

  27. Unreal Robotics Lab: A High-Fidelity Robotics Simulator with Advanced Physics and Rendering

    cs.RO 2025-04 unverdicted novelty 5.0

    Unreal Robotics Lab integrates Unreal Engine rendering with MuJoCo physics to enable high-fidelity simulation for robotics perception, control, and benchmarking under diverse conditions.

  28. Long-Distance Real-World Navigation of the Legged-Wheeled Robot Go2-W Using Deep Reinforcement Learning

    cs.RO 2026-06 unverdicted novelty 4.0

    A DRL locomotion controller extended from prior quadruped work enabled the Go2-W robot to complete 2.8 km of autonomous real-world navigation including mixed terrain and stairs.

  29. ReFPO: Reflow Regularization for Flow Matching Policy Gradients

    cs.RO 2026-06 unverdicted novelty 4.0

    ReFPO adds explicit Reflow regularization to FPO, stabilizing PPO-style training and supporting high-fidelity one-step inference across GridWorld, MuJoCo, and Humanoid tasks.

  30. Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It)

    cs.RO 2026-05 unverdicted novelty 4.0

    Excessive sim2real focus impedes robotics policy learning via simulator lock-in; a kinematics-only sim2sim2real paradigm is proposed to restore exploration.

  31. Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient

    cs.RO 2026-05 unverdicted novelty 4.0

    SDPG is a new on-policy visual RL algorithm that estimates gradients via stochastic perturbations of rollouts, achieving faster training and lower memory use than baselines on visual MuJoCo tasks while adding new robo...

  32. Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System

    cs.RO 2026-06 unverdicted novelty 3.0

    Zero-shot sim-to-real transfer of independently trained RL policies for cart-pole swing-up and stabilization is achieved via sensitivity-guided domain randomization, linear curriculum learning, and first-order action ...