Pith. sign in

REVIEW 12 cited by

A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2208.07860 v1 pith:X4JKJ3ZE submitted 2022-08-16 cs.RO cs.AI

Laura Smith , Ilya Kostrikov , Sergey Levine This is my paper · ORCID
classification cs.ROcs.AI
keywords learningapproachdeepenvironmentsevaluateminutesreinforcementrobot
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Deep reinforcement learning is a promising approach to learning policies in uncontrolled environments that do not require domain knowledge. Unfortunately, due to sample inefficiency, deep RL applications have primarily focused on simulated environments. In this work, we demonstrate that the recent advancements in machine learning algorithms and libraries combined with a carefully tuned robot controller lead to learning quadruped locomotion in only 20 minutes in the real world. We evaluate our approach on several indoor and outdoor terrains which are known to be challenging for classical model-based controllers. We observe the robot to be able to learn walking gait consistently on all of these terrains. Finally, we evaluate our design decisions in a simulated environment.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

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

  1. SpikeATac: A Multimodal Tactile Finger with Taxelized Dynamic Sensing for Dexterous Manipulation

    cs.RO 2025-10 conditional novelty 7.0 of 10

    A fingertip with 16-taxel PVDF dynamic sensing plus capacitive static sensing enables fast delicate grasping and, with RLHF fine-tuning, in-hand manipulation of fragile objects.

  2. Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments

    cs.LG 2025-05 conditional novelty 7.0 of 10

    Across noisy DeepMind Control tasks, explicit bisimulation-metric losses add little denoising benefit beyond plain self-prediction and feature normalization, which dominate performance.

  3. SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows

    cs.RO 2026-02 unverdicted novelty 6.0 of 10

    SERNF fine-tunes dexterous manipulation policies on real hardware by pairing normalizing-flow policies with action-chunked critics and conservative off-policy RL.

  4. Touch begins where vision ends: Generalizable policies for contact-rich manipulation

    cs.RO 2025-06 conditional novelty 6.0 of 10

    A localize-then-execute policy that combines vision-language reaching, semantic background augmentation, and residual reinforcement learning with tactile sensing reaches about 90% success on millimeter-precision manip...

  5. Growable and Interpretable Neural Control with Online Continual Learning for Autonomous Lifelong Locomotion Learning Machines

    cs.RO 2025-05 conditional novelty 6.0 of 10

    A hexapod using GOLLUM autonomously learned multiple locomotion skills in about an hour by growing new neural subnetworks for new conditions and by blending previously learned skills through supplementary connections.

  6. Towards Embodiment Scaling Laws in Robot Locomotion

    cs.RO 2025-05 conditional novelty 6.0 of 10

    A policy trained on about one thousand simulated robot bodies generalizes progressively better to unseen bodies as the number of training bodies grows, and it transfers zero-shot to two real robots.

  7. Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning

    cs.RO 2025-02 conditional novelty 6.0 of 10

    SGFT uses a simulation-trained value function to guide real-world exploration via potential-based reward shaping and short-horizon objectives, substantially improving fine-tuning sample efficiency.

  8. MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization

    cs.LG 2024-12 conditional novelty 6.0 of 10

    MaxInfoRL augments Boltzmann exploration with an auto-tuned information-gain bonus and reports consistent gains over SAC, DrQ, and DrQv2 baselines on continuous control tasks.

  9. What Matters for Simulation to Online Reinforcement Learning on Real Robots

    cs.RO 2026-02 conditional novelty 5.0 of 10

    Sim-to-online RL on three real robots is stabilized by retaining data, warm-starting the replay buffer, and using asymmetric actor-critic updates with a low actor learning rate.

  10. Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents

    cs.LG 2025-10 conditional novelty 5.0 of 10

    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.

  11. SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training

    cs.RO 2025-06 conditional novelty 5.0 of 10

    SLAC learns a latent action space in a low-fidelity simulator and uses it for real-world reinforcement learning, solving whole-body mobile manipulation tasks in under an hour without demonstrations.

  12. GainAdaptor: Learning Quadrupedal Locomotion with Dual Actors for Adaptable and Energy-Efficient Walking on Various Terrains

    cs.RO 2024-12 conditional novelty 4.0 of 10

    GainAdaptor learns to adjust both joint positions and PD gains with two neural network actors, cutting power use on a Unitree Go1 across varied terrains.

Pith tools