Pith. sign in

REVIEW 5 cited by

Reinforcement Learning with Augmented Data

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 2004.14990 v5 pith:AEAV7RLW submitted 2020-04-30 cs.LG stat.ML

Michael Laskin , Kimin Lee , Adam Stooke , Lerrel Pinto , Pieter Abbeel , Aravind Srinivas This is my paper
classification cs.LGstat.ML
keywords learningdatarandomaugmentationscontrolmethodsreinforcementalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks have proved to be a recipe for success, current methods are still lacking on two fronts: (a) data-efficiency of learning and (b) generalization to new environments. To this end, we present Reinforcement Learning with Augmented Data (RAD), a simple plug-and-play module that can enhance most RL algorithms. We perform the first extensive study of general data augmentations for RL on both pixel-based and state-based inputs, and introduce two new data augmentations - random translate and random amplitude scale. We show that augmentations such as random translate, crop, color jitter, patch cutout, random convolutions, and amplitude scale can enable simple RL algorithms to outperform complex state-of-the-art methods across common benchmarks. RAD sets a new state-of-the-art in terms of data-efficiency and final performance on the DeepMind Control Suite benchmark for pixel-based control as well as OpenAI Gym benchmark for state-based control. We further demonstrate that RAD significantly improves test-time generalization over existing methods on several OpenAI ProcGen benchmarks. Our RAD module and training code are available at https://www.github.com/MishaLaskin/rad.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning

    cs.CV 2025-06 conditional novelty 7.0 of 10

    A self-supervised auxiliary loss combining weak and strong augmentations, an adversarial discriminator, and inverse-then-forward latent dynamics improves both data efficiency and zero-shot generalization in vision-based RL.

  2. SymmGrid: Super-Scaling On-Robot Learning with Parallelized Symmetries and Egocentric-Exocentric Visual Perception

    cs.RO 2026-07 conditional novelty 5.0 of 10

    Grid-parallel translational trajectory symmetries plus sample-time homographies cut on-robot RL wall-clock training 1.37–2.17× versus SERL on three real contact tasks.

  3. FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing

    cs.CV 2026-07 conditional novelty 5.0 of 10

    FAS-R1 combines long-CoT supervised fine-tuning with difficulty-aware GRPO and degradation-simulated augmentation to improve multi-task face anti-spoofing and explainable rationales.

  4. Trading Human Curation for Synthetic Augmentation in RLVR

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    Gated synthetic augmentations of a 10-task human base substitute for ~87 extra human RLVR tasks on aggregate held-out pass@1, with cost-adjusted trade rate ρ_cost in [1.4×, 11.6×].

  5. A Survey of State Representation Learning for Deep Reinforcement Learning

    cs.LG 2025-06 conditional novelty 4.0 of 10

    A six-class taxonomy of state representation learning methods for model-free online deep reinforcement learning, with selection guidelines, evaluation metrics, and future directions.

Pith tools