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
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
Forward citations
Cited by 7 Pith papers
-
Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
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.
-
Good Rankers, Bad Objectives: Bilinear Contrastive Critics under Expressive Policy Search
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.
-
Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?
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...
-
OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies
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.
-
Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
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.
-
Value Flows
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.
-
Reinforcement Learning: From Algorithms To Foundation Models
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.
Discussion (0). Continue with ORCID to comment.