Pith. sign in

REVIEW 10 cited by

Learning Latent Plans from Play

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 1903.01973 v2 pith:PEYB76AQ submitted 2019-03-05 cs.RO

Learning Latent Plans from Play

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

Acquiring a diverse repertoire of general-purpose skills remains an open challenge for robotics. In this work, we propose self-supervising control on top of human teleoperated play data as a way to scale up skill learning. Play has two properties that make it attractive compared to conventional task demonstrations. Play is cheap, as it can be collected in large quantities quickly without task segmenting, labeling, or resetting to an initial state. Play is naturally rich, covering ~4x more interaction space than task demonstrations for the same amount of collection time. To learn control from play, we introduce Play-LMP, a self-supervised method that learns to organize play behaviors in a latent space, then reuse them at test time to achieve specific goals. Combining self-supervised control with a diverse play dataset shifts the focus of skill learning from a narrow and discrete set of tasks to the full continuum of behaviors available in an environment. We find that this combination generalizes well empirically---after self-supervising on unlabeled play, our method substantially outperforms individual expert-trained policies on 18 difficult user-specified visual manipulation tasks in a simulated robotic tabletop environment. We additionally find that play-supervised models, unlike their expert-trained counterparts, are more robust to perturbations and exhibit retrying-till-success behaviors. Finally, we find that our agent organizes its latent plan space around functional tasks, despite never being trained with task labels. Videos, code and data are available at learning-from-play.github.io

discussion (0)

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

Forward citations

Cited by 10 Pith papers

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

  1. Solving Rubik's Cube with a Robot Hand

    cs.LG 2019-10 accept novelty 7.0

    Reinforcement learning models trained only in simulation using automatic domain randomization solve Rubik's cube with a real robot hand.

  2. Continuous Reasoning for Vision-Language-Action

    cs.RO 2026-05 unverdicted novelty 6.0

    Continuous Reasoning for VLA introduces a shared Gaussian latent for continuous thoughts, trained with self-verification to improve action prediction on LIBERO-PRO and real robots.

  3. CA2: Code-Aware Agent for Automated Game Testing

    cs.SE 2026-05 unverdicted novelty 6.0

    CA2 integrates call stack information into RL agents for game testing and shows consistent gains over baselines that ignore code signals.

  4. Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 6.0

    Ms.PR applies multi-scale predictive supervision to enforce goal-directed alignment in latent spaces for offline GCRL, yielding improved representation quality and performance on vision and state-based tasks.

  5. QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation

    cs.RO 2026-04 unverdicted novelty 6.0

    QDTraj uses Quality-Diversity algorithms with sparse rewards to produce at least five times more diverse high-performing trajectories for articulated object manipulation than compared methods, validated across 30 obje...

  6. AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation

    cs.RO 2025-10 unverdicted novelty 6.0

    AFFORD2ACT distills a minimal set of affordance-guided 2D keypoints from text and a single image to train a 38-dimensional gated transformer policy that achieves 82% success on unseen objects and scenes.

  7. Training Language Models to Self-Correct via Reinforcement Learning

    cs.LG 2024-09 unverdicted novelty 6.0

    SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.

  8. RoboNet: Large-Scale Multi-Robot Learning

    cs.RO 2019-10 conditional novelty 6.0

    RoboNet is a multi-robot video dataset that enables pre-training of vision-based manipulation models which, after fine-tuning on a new robot, outperform robot-specific training that uses 4-20 times more data.

  9. Leveraging VR Robot Games to Facilitate Data Collection for Embodied Intelligence Tasks

    cs.RO 2026-04 unverdicted novelty 4.0

    A VR gamified data collection system in Unity for humanoid robots demonstrates broad state-action coverage in pick-and-place tasks, with higher difficulty increasing motion intensity and workspace exploration.

  10. On Multi-Agent Learning in Team Sports Games

    cs.MA 2019-06 unverdicted novelty 3.0

    Describes a hierarchical RL method for multi-agent learning in team sports games aiming for human-like agents, reporting preliminary results that show promise.