Pith. sign in

REVIEW 6 cited by

A Survey of Exploration Methods in Reinforcement Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2109.00157 v2 pith:4VJDD6XE submitted 2021-09-01 cs.LG cs.AI

Susan Amin , Maziar Gomrokchi , Harsh Satija , Herke van Hoof , Doina Precup This is my paper · ORCID
classification cs.LGcs.AI
keywords learningexplorationreinforcementmethodsagentssurveyalgorithmsarticle
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Exploration is an essential component of reinforcement learning algorithms, where agents need to learn how to predict and control unknown and often stochastic environments. Reinforcement learning agents depend crucially on exploration to obtain informative data for the learning process as the lack of enough information could hinder effective learning. In this article, we provide a survey of modern exploration methods in (Sequential) reinforcement learning, as well as a taxonomy of exploration methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Towards Human-level Dexterity via Robot Learning

    cs.RO 2025-07 conditional novelty 6.0 of 10

    Sampling-based planning used for reset states and pre-training makes reinforcement learning practical for dexterous in-hand manipulation of hard objects with intrinsic sensing.

  2. Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Sampling a random hypersphere point from a von Mises-Fisher distribution around the state and retrieving its nearest neighbor asymptotically reproduces Boltzmann exploration probabilities at sublinear cost.

  3. LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback

    cs.AI 2026-07 conditional novelty 5.0 of 10

    LEMUR jointly learns a separate reward model for each teacher's preferences and uses them to train a population of multi-objective policies, beating baselines that merge feedback into one reward.

  4. CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

    cs.CL 2025-09 conditional novelty 5.0 of 10

    Adding actor perplexity and multi-head critic variance as intrinsic exploration bonuses improves RLVR math reasoning accuracy by roughly +2 to +3 points on AIME benchmarks.

  5. Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

    cs.LG 2025-08 conditional novelty 5.0 of 10

    Using Pass@k as an RLVR reward, with bootstrap sampling and an analytical advantage formula, improves exploration and later Pass@1 performance of reasoning LLMs.

  6. Contextual Multi-Task Reinforcement Learning for Autonomous Reef Monitoring

    cs.RO 2026-04 unverdicted novelty 4.0 of 10

    Contextual multi-task DDQN learns one AUV policy for multiple simulated reef-monitoring tasks that matches mixture-of-experts performance and generalizes better on a discrete toy domain.

Pith tools