REVIEW 15 cited by
Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning
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
Signed reviews
read the original abstract
In this work, we present and study a training set-up that achieves fast policy generation for real-world robotic tasks by using massive parallelism on a single workstation GPU. We analyze and discuss the impact of different training algorithm components in the massively parallel regime on the final policy performance and training times. In addition, we present a novel game-inspired curriculum that is well suited for training with thousands of simulated robots in parallel. We evaluate the approach by training the quadrupedal robot ANYmal to walk on challenging terrain. The parallel approach allows training policies for flat terrain in under four minutes, and in twenty minutes for uneven terrain. This represents a speedup of multiple orders of magnitude compared to previous work. Finally, we transfer the policies to the real robot to validate the approach. We open-source our training code to help accelerate further research in the field of learned legged locomotion.
Forward citations
Cited by 15 Pith papers
-
When Is a Learned Command Adapter Worth It? Closed-Loop Identification and Counterfactual Auditing of Frozen Locomotion Policies
A counterfactual audit separates same-state headroom from recoverable state-allocation gain, returning NO-GO or ABSTAIN for learned command adapters on frozen Go2 and H1 locomotion policies at 1% thresholds.
-
Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.
-
Learning to Walk in Costume: Adversarial Motion Priors for Aesthetically Constrained Humanoids
A reinforcement learning controller with human-motion imitation priors produced stable standing and walking on Cosmo, a top-heavy, vision-less entertainment humanoid with shell-restricted joints.
-
MULE: Multi-terrain and Unknown Load Adaptation for Effective Quadrupedal Locomotion
A two-phase RL framework with a nominal policy and a GRF-rewarded adaptive policy improves payload adaptation for quadrupedal locomotion across varied terrains.
-
Bridging Adaptivity and Safety: Learning Agile Collision-Free Locomotion Across Varied Physics
A legged-robot controller that estimates payload and friction online and uses those estimates to switch between agile and recovery policies achieves lower collision rates and higher speeds than non-adaptive baselines.
-
GASP: GPU-Accelerated Safe Planner for Real-Time Collision-Aware Motion Generation with Latent Trajectory Sampling
A learned B-spline planner with latent sampling generates collision-aware joint trajectories on the GPU in near-millisecond time, matching analytical planners and outperforming a GPU optimization baseline.
-
Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning
A VR-teleoperated, reinforcement-learning-balanced control stack lets a miniature ROBOTIS OP3 humanoid walk and manipulate objects simultaneously.
-
Milo, a Fully Autonomous Indoor/Outdoor Robotic Guide Dog
Milo is an open-source, fully onboard robotic guide dog that navigates unseen indoor/outdoor paths while explicitly modeling the handler's position, with preliminary real-world tests against a handler-unaware costmap ...
-
Sim2Swim: Zero-Shot Velocity Control for Agile AUV Maneuvering in 3 Minutes
A DRL velocity controller for AUVs, trained in under 3 minutes in simulation, transfers zero-shot to a real underwater vehicle for agile 6DOF path-following.
-
KiVi: Kinesthetic-Visuospatial Integration for Dynamic and Safe Egocentric Legged Locomotion
A quadruped locomotion controller that explicitly separates proprioceptive and visual pathways stays stable under camera occlusion and visual corruption that destabilizes fused-vision policies.
-
HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mamba
A single-layer Mamba encoder as the policy backbone improves learning speed, stability, and energy efficiency of an end-to-end RL humanoid walking controller in simulation compared to a feedforward baseline.
-
APEX: Action Priors Enable Efficient Exploration for Robust Motion Tracking on Legged Robots
APEX trains gait-tracking policies with decaying action priors and separate style and task critics, achieving reference-free deployment, faster convergence, and reward-robustness over DeepMimic.
-
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
RoboVerse unifies seven simulators, 15 benchmarks, and 510.5k migrated trajectories into one platform with a four-level generalization benchmark, claiming better robot learning and sim-to-real transfer.
-
UMC: Unified Resilient Controller for Legged Robots with Joint Malfunctions
UMC uses masked attention and two-stage training so one policy keeps legged robots walking under eight sensor and joint failure scenarios, cutting fall rates by up to 53 percentage points in simulation.
-
D4W: Dependable Data-Driven Dynamics for Wheeled Robots
A data-driven simulator that learns wheeled-robot dynamics from real motion capture data and beats analytical simulators on long-horizon trajectory prediction.
Discussion (0). Continue with ORCID to comment.