Pith. sign in

REVIEW 3 cited by

Reward Uncertainty for Exploration in Preference-based 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 2205.12401 v1 pith:7WB6AHF3 submitted 2022-05-24 cs.LG cs.AI

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

Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating human feedback, i.e. teacher's preferences between two clips of behaviors. However, poor feedback-efficiency still remains a problem in current preference-based RL algorithms, as tailored human feedback is very expensive. To handle this issue, previous methods have mainly focused on improving query selection and policy initialization. At the same time, recent exploration methods have proven to be a recipe for improving sample-efficiency in RL. We present an exploration method specifically for preference-based RL algorithms. Our main idea is to design an intrinsic reward by measuring the novelty based on learned reward. Specifically, we utilize disagreement across ensemble of learned reward models. Our intuition is that disagreement in learned reward model reflects uncertainty in tailored human feedback and could be useful for exploration. Our experiments show that exploration bonus from uncertainty in learned reward improves both feedback- and sample-efficiency of preference-based RL algorithms on complex robot manipulation tasks from MetaWorld benchmarks, compared with other existing exploration methods that measure the novelty of state visitation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries

    cs.LG 2025-05 conditional novelty 6.0 of 10

    CLARIFY uses contrastive learning on preference data to embed trajectories, then rejection-samples queries that humans can distinguish clearly, improving offline preference-based RL.

  2. Residual Reward Models for Preference-based Reinforcement Learning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Combining a hand-designed or learned prior reward with a preference-trained residual improves sample efficiency and final performance in preference-based reinforcement learning.

  3. Towards Reliable, Uncertainty-Aware Alignment

    cs.LG 2025-07 reject novelty 4.0 of 10

    Variance-aware RLHF adds a variance-weighted KL penalty to PPO and reduces reward variance and the risk of underperforming the reference policy in the paper's experiments.

Pith tools