Pith. sign in

REVIEW 25 cited by

Mastering Visual Continuous Control: Improved Data-Augmented 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

arxiv 2107.09645 v1 pith:FQLV5H64 submitted 2021-07-20 cs.AI cs.LG

classification cs.AIcs.LG
keywords drq-v2controlcontinuousdirectlylearningmodel-freereinforcementtasks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data augmentation to learn directly from pixels. We introduce several improvements that yield state-of-the-art results on the DeepMind Control Suite. Notably, DrQ-v2 is able to solve complex humanoid locomotion tasks directly from pixel observations, previously unattained by model-free RL. DrQ-v2 is conceptually simple, easy to implement, and provides significantly better computational footprint compared to prior work, with the majority of tasks taking just 8 hours to train on a single GPU. Finally, we publicly release DrQ-v2's implementation to provide RL practitioners with a strong and computationally efficient baseline.

Discussion (0). Sign in to comment.

Forward citations

Cited by 25 Pith papers

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

  1. Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.

  2. Operator-Guided Invariance Learning for Continuous Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    VPSD-RL discovers exact and approximate value-preserving Lie-group operators in continuous RL to stabilize learning via transition augmentation and consistency regularization.

  3. Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations

    cs.RO 2026-04 unverdicted novelty 7.0 of 10

    ACO-MoE employs agent-centric mixture-of-experts to decouple task-relevant features from dynamic visual perturbations in RL, recovering 95.3% of clean performance on the new VDCS benchmark.

  4. Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations

    cs.RO 2026-04 unverdicted novelty 7.0 of 10

    ACO-MoE recovers 95.3% of clean-input performance in visual control tasks under Markov-switching corruptions by routing restoration experts and anchoring representations to clean foreground masks.

  5. Mastering Diverse Domains through World Models

    cs.AI 2023-01 unverdicted novelty 7.0 of 10

    DreamerV3 uses world models and robustness techniques to solve over 150 tasks across domains with a single configuration, including Minecraft diamond collection from scratch.

  6. OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies

    cs.RO 2026-07 conditional novelty 6.0 of 10

    A policy-agnostic two-stage real-world RL method learns tactile residual corrections on frozen visual policies, lifting contact-rich task success from 5–40% to 85–100% in under 80 minutes.

  7. Rank-Then-Act: Reward-Free Control from Frame-Order Progress

    cs.LG 2026-07 unverdicted novelty 6.0 of 10

    RTA trains a VLM as a progress ordinal scorer via GRPO on shuffled expert frames and uses Spearman rank correlation with temporal indices as a bounded RL reward, matching or exceeding prior video reward methods on dis...

  8. RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation

    cs.RO 2026-06 unverdicted novelty 6.0 of 10

    RARM is a lightweight visual comparator trained once on general videos that supplies dense progress rewards to RL by matching rollout clips to a reference demonstration and gating rewards on match confidence.

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

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    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...

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

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    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.

  11. Error Amplification Limits ANN-to-SNN Conversion in Continuous Control

    cs.NE 2026-01 conditional novelty 6.0 of 10

    Temporally correlated action errors, amplified by closed-loop dynamics, explain ANN-to-SNN conversion failures in continuous control, and cross-step residual potential initialization mitigates them.

  12. Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning Approach

    cs.AI 2025-10 conditional novelty 6.0 of 10

    A sample-efficient SAC-based method with replay-ratio resets, offline data bootstrapping, and expert-driven fine-tuning produces a goalkeeper that outperforms the built-in AI in EA SPORTS FC 25.

  13. TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance

    cs.AI 2025-09 unverdicted novelty 6.0 of 10

    TimeRewarder derives step-wise progress rewards from frame-wise temporal distances in passive videos and uses them to guide RL, achieving high success rates on Meta-World tasks with fewer interactions than prior metho...

  14. DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in Manipulation

    cs.RO 2025-09 conditional novelty 6.0 of 10

    Depth-guided masking improves visual RL generalization, sample efficiency, and interpretability on manipulation tasks.

  15. HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model

    cs.CV 2025-03 unverdicted novelty 6.0 of 10

    HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.

  16. Differential Amplifier-Inspired AmpAttention for Multi-View Robotic Manipulation

    cs.RO 2026-07 conditional novelty 5.0 of 10

    AmpAttention and RVAF raise multi-view robotic manipulation success and cut training time by suppressing attention noise with a differential-amplifier-style mechanism plus a CMRR loss.

  17. 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.

  18. ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning

    cs.RO 2025-12 conditional novelty 5.0 of 10

    ReinforceGen uses imitation learning, RL fine-tuning of skill policies, and real-time pose replanning to reach over 80% success on five long-horizon Robosuite tasks from only 10 human demonstrations.

  19. RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation

    cs.RO 2025-10 unverdicted novelty 5.0 of 10

    Abstract describes RoDyn but full text describes iMoWM; the record is internally inconsistent and the headline claims are absent from the body.

  20. TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance

    cs.AI 2025-09 unverdicted novelty 5.0 of 10

    TimeRewarder derives progress-based dense rewards from passive videos via frame-wise temporal distance modeling and uses them as proxy rewards to boost RL success on Meta-World tasks.

  21. LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning

    cs.RO 2025-09 unverdicted novelty 5.0 of 10

    LLM-TALE steers RL exploration using LLM-generated plans at task and affordance levels with online suboptimality correction, improving sample efficiency and success rates on pick-and-place tasks without human supervision.

  22. Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own

    cs.RO 2023-10 unverdicted novelty 5.0 of 10

    RLFP and the FAC algorithm combine foundation-model priors for policy, value, and rewards to produce sample-efficient robotic RL that reaches 86% real-robot success after one hour and 100% success on 7/8 Meta-world ta...

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

    cs.RO 2026-05 unverdicted novelty 4.0 of 10

    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...

  24. Balancing Plasticity and Stability with Fast and Slow Successor Features

    cs.LG 2026-05 unverdicted novelty 4.0 of 10

    Synaptic consolidation applied to multi-timescale successor features yields better performance than plasticity-focused methods in RL under gradual environmental drift.

  25. Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms

    cs.RO 2026-05 unverdicted novelty 4.0 of 10

    A survey proposing a hierarchical taxonomy for multimodal tactile fusion datasets and methods across perception, generation, and interaction in embodied intelligence.

Pith tools