Pith. sign in

REVIEW 7 cited by

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

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 2303.05479 v4 pith:FZ4UK7JI submitted 2023-03-09 cs.LG cs.AI

classification cs.LGcs.AI
keywords offlinefine-tuningcal-qlonlinepolicyvaluecalibratedlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interaction. However, existing offline RL methods tend to behave poorly during fine-tuning. In this paper, we devise an approach for learning an effective initialization from offline data that also enables fast online fine-tuning capabilities. Our approach, calibrated Q-learning (Cal-QL), accomplishes this by learning a conservative value function initialization that underestimates the value of the learned policy from offline data, while also being calibrated, in the sense that the learned Q-values are at a reasonable scale. We refer to this property as calibration, and define it formally as providing a lower bound on the true value function of the learned policy and an upper bound on the value of some other (suboptimal) reference policy, which may simply be the behavior policy. We show that offline RL algorithms that learn such calibrated value functions lead to effective online fine-tuning, enabling us to take the benefits of offline initializations in online fine-tuning. In practice, Cal-QL can be implemented on top of the conservative Q learning (CQL) for offline RL within a one-line code change. Empirically, Cal-QL outperforms state-of-the-art methods on 9/11 fine-tuning benchmark tasks that we study in this paper. Code and video are available at https://nakamotoo.github.io/Cal-QL

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 20 citations worldwide. Full citation record

  1. Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

    cs.RO 2026-08 conditional novelty 6.0 of 10

    A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.

  2. Good Rankers, Bad Objectives: Bilinear Contrastive Critics under Expressive Policy Search

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Bilinear contrastive critics remain good compatibility rankers but are unsafe to maximize for action selection; cosine bounding does not fix value decalibration, while Bellman TD-Q does.

  3. 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...

  4. 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.

  5. 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.

  6. 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.

  7. Reinforcement Learning: From Algorithms To Foundation Models

    cs.AI 2026-07 conditional novelty 3.0 of 10

    A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.

Pith tools