mlsanityData to 7 Oct 2026

Deep Exploration via Randomized Value Functions

arXiv 1703.07608 ↗First posted 22 Mar 2017stat.ML cs.AI cs.LGcited by 155

Not on the map. Why?

Abstract (arXiv)

We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to value function learning. We present several reinforcement learning algorithms that leverage randomized value functions and demonstrate their efficacy through computational studies. We also prove a regret bound that establishes statistical efficiency with a tabular representation.

Key facts. Cited by 155 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 33; 2022: 24; 2023: 34; 2024: 24; 2025: 20; 2026: 19.

155 papers.

Sort:

By area:

  1. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationcited by 223
  2. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 158
  3. 2024BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulationcited by 140
  4. 2021Epistemic Neural Networkscited by 120
  5. 2021Repulsive Deep Ensembles are Bayesiancited by 103
  6. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  7. 2022Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matterscited by 74
  8. 2022q-Learning in Continuous Timecited by 68
  9. 2021Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learningcited by 65
  10. 2021Reinforcement Learning, Bit by Bitcited by 59
  11. 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
  12. 2021Randomized Exploration for Reinforcement Learning with General Value Function Approximationcited by 49
38 more
  1. 2024Efficient Exploration for LLMscited by 44
  2. 2020Overcoming Model Bias for Robust Offline Deep Reinforcement Learningcited by 42
  3. 2021Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent Statescited by 42
  4. 2021MADE: Exploration via Maximizing Deviation from Explored Regionscited by 40
  5. 2021Interesting Object, Curious Agent: Learning Task-Agnostic Explorationcited by 38
  6. 2021Learning more skills through optimistic explorationcited by 37
  7. 2022A Review of Uncertainty for Deep Reinforcement Learningcited by 36
  8. 2023Approximate Thompson Sampling via Epistemic Neural Networkscited by 31
  9. 2023Thompson sampling for improved exploration in GFlowNetscited by 31
  10. 2022Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximationcited by 29
  11. 2023Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlocited by 29
  12. 2021Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environmentscited by 28
  13. 2023Planning Goals for Explorationcited by 28
  14. 2025Diversity-Incentivized Exploration for Versatile Reasoningcited by 28
  15. 2021Discovery of Options via Meta-Learned Subgoalscited by 27
  16. 2021Principled Exploration via Optimistic Bootstrapping and Backward Inductioncited by 26
  17. 2022Sample Efficient Deep Reinforcement Learning via Uncertainty Estimationcited by 26
  18. 2022Regret Bounds for Information-Directed Reinforcement Learningcited by 24
  19. 2021Deciding What to Learn: A Rate-Distortion Approachcited by 23
  20. 2022An Analysis of Ensemble Samplingcited by 23
  21. 2022From Dirichlet to Rubin: Optimistic Exploration in RL without Bonusescited by 22
  22. 2021An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learningcited by 20
  23. 2024A social path to human-like artificial intelligencecited by 20
  24. 2022Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learningcited by 19
  25. 2021Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Roboticscited by 18
  26. 2021Collect & Infer -- a fresh look at data-efficient Reinforcement Learningcited by 17
  27. 2021Bayesian Bellman Operatorscited by 16
  28. 2023Posterior Sampling for Deep Reinforcement Learningcited by 16
  29. 2025Representation-Based Exploration for Language Models: From Test-Time to Post-Trainingcited by 16
  30. 2021Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximationcited by 15
  31. 2021The Value of Information When Deciding What to Learncited by 15
  32. 2023Model-Based Uncertainty in Value Functionscited by 15
  33. 2025Toward Efficient Exploration by Large Language Model Agentscited by 15
  34. 2021Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learningcited by 14
  35. 2021Near-Optimal Randomized Exploration for Tabular Markov Decision Processescited by 14
  36. 2021Deep Exploration for Recommendation Systemscited by 14
  37. 2022Model-Based Reinforcement Learning with Multinomial Logistic Function Approximationcited by 13
  38. 2022Representation Learning in Deep RL via Discrete Information Bottleneckcited by 13

50 most cited of 155 All 155 (JSON)