Pith. sign in

REVIEW 5 cited by

Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions

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 2303.17396 v1 pith:KHA2LDXT submitted 2023-03-30 cs.LG

classification cs.LG
keywords offlineonlinelearningpolicyfinetuningperformanceagentsalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Offline reinforcement learning (RL) allows for the training of competent agents from offline datasets without any interaction with the environment. Online finetuning of such offline models can further improve performance. But how should we ideally finetune agents obtained from offline RL training? While offline RL algorithms can in principle be used for finetuning, in practice, their online performance improves slowly. In contrast, we show that it is possible to use standard online off-policy algorithms for faster improvement. However, we find this approach may suffer from policy collapse, where the policy undergoes severe performance deterioration during initial online learning. We investigate the issue of policy collapse and how it relates to data diversity, algorithm choices and online replay distribution. Based on these insights, we propose a conservative policy optimization procedure that can achieve stable and sample-efficient online learning from offline pretraining.

Discussion (0). Continue with ORCID 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. Evaluating Fuzz Testing for Reinforcement Learning Agents

    cs.LG 2026-07 accept novelty 6.0 of 10

    Under unified budgets, MDPFuzz leads crash count and speed; SeqDivFuzz leads diversity; fuzz crashes improve robustness and train cross-fuzzer safety monitors.

  2. Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Reliable history-conditioned value functions enable value-guided offline-to-online RL that scales better than behavior cloning and stabilizes online adaptation on hard real-robot tasks.

  3. Fine-Tuning without Performance Degradation

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Automatic Jump Start uses Fitted Q Evaluation to adapt the Jump-Start exploration schedule, reducing fine-tuning performance degradation without tuning a tolerance threshold.

  4. 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.

  5. 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.

Pith tools