Pith. sign in

REVIEW 11 cited by

Efficient Online Reinforcement Learning with Offline Data

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 2302.02948 v4 pith:2WNJ33BK submitted 2023-02-06 cs.LG cs.AI

classification cs.LGcs.AI
keywords dataexistinglearningofflineonlineadditionalapplyexpert
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human expert or a sub-optimal exploration policy. Previous methods have relied on extensive modifications and additional complexity to ensure the effective use of this data. Instead, we ask: can we simply apply existing off-policy methods to leverage offline data when learning online? In this work, we demonstrate that the answer is yes; however, a set of minimal but important changes to existing off-policy RL algorithms are required to achieve reliable performance. We extensively ablate these design choices, demonstrating the key factors that most affect performance, and arrive at a set of recommendations that practitioners can readily apply, whether their data comprise a small number of expert demonstrations or large volumes of sub-optimal trajectories. We see that correct application of these simple recommendations can provide a $\mathbf{2.5\times}$ improvement over existing approaches across a diverse set of competitive benchmarks, with no additional computational overhead. We have released our code at https://github.com/ikostrikov/rlpd.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

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

  1. Adaptation of Generalist Robot Policies with Minimal Data

    cs.RO 2026-08 conditional novelty 6.0 of 10

    MiDAS, a two-stage recipe of one-demo behavior cloning plus residual online RL on a frozen VLA backbone, reaches high success from a single demonstration in simulation and improves real-world bimanual manipulation.

  2. Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?

    cs.LG 2026-07 conditional novelty 6.0 of 10

    On six robot-manipulation tasks, offline Q-pretraining does not accelerate online RL fine-tuning from a pretrained policy, while seeding the replay buffer with rollouts from an ensemble of policies (IPE) improves fina...

  3. 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.

  4. Online World Modeling Enables Real-World Inverse Reinforcement Learning from Observation

    cs.RO 2026-02 conditional novelty 6.0 of 10

    MPAIL2 demonstrates real-world manipulation learning from observation alone, without rewards or action labels, plus positive online transfer.

  5. Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning

    cs.RO 2025-11 unverdicted novelty 6.0 of 10

    MSDP pre-trains a transformer encoder with masked multisensory autoencoding, then uses an asymmetric actor-critic bridge (cross-attention for critic, pooling for actor) to accelerate and robustify contact-rich RL acro...

  6. Decentralized Relaxed Smooth Optimization with Gradient Descent Methods

    math.OC 2025-08 unverdicted novelty 6.0 of 10

    A decentralized gradient descent method with adaptive clipping is claimed to reach best-known convergence rates for convex and nonconvex problems under (L0,L1)-smoothness without knowing the constants.

  7. Reinforcement Learning via Implicit Imitation Guidance

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A reinforcement learning method that learns a state-dependent covariance from expert-policy action differences and uses it as exploration noise, improving sample efficiency on sparse-reward continuous control tasks.

  8. Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL

    cs.LG 2025-05 conditional novelty 6.0 of 10

    SSAR replaces the fixed global regularization strength in offline RL with state-adaptive coefficients and applies regularization only to high-quality actions, improving D4RL performance over CQL and TD3+BC.

  9. Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A three-component framework (policy re-evaluation, value alignment, constrained fine-tuning) improves stable fine-tuning from offline RL policies to SAC, TD3, and PPO.

  10. Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

    cs.LG 2024-12 conditional novelty 6.0 of 10

    Warm-start RL (WSRL) fine-tunes offline-pretrained RL agents online with no offline data retention, using 5,000 warm-up rollouts from the frozen pre-trained policy followed by standard high-UTD SAC.

  11. Value Flows

    cs.LG 2025-10 reject novelty 5.0 of 10

    Value Flows fits the full return distribution in RL with a flow-matching critic and reweights its learning objective by estimated return variance; the central theoretical guarantee does not follow from the stated equations.

Pith tools