mlsanityData to 7 Oct 2026

Data-Driven Evaluation of Training Action Space for Reinforcement Learning

arXiv 2204.03840 ↗First posted 8 Apr 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Training action space selection for reinforcement learning (RL) is conflict-prone due to complex state-action relationships. To address this challenge, this paper proposes a Shapley-inspired methodology for training action space categorization and ranking. To reduce exponential-time shapley computations, the methodology includes a Monte Carlo simulation to avoid unnecessary explorations. The effectiveness of the methodology is illustrated using a cloud infrastructure resource tuning case study. It reduces the search space by 80% and categorizes the training action sets into dispensable and indispensable groups. Additionally, it ranks different training actions to facilitate high-performance yet cost-efficient RL model design. The proposed data-driven methodology is extensible to different domains, use cases, and reinforcement learning algorithms.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 55 references that are in the map. First posted on arXiv 8 Apr 2022.

Builds on

24 of 55 references.

References · 24

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
  3. 2019Agnostic Federated Learningcited by 451
  4. 2019The many Shapley values for model explanationcited by 341
  5. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  6. 2016Contextual Decision Processes with Low Bellman Rank are PAC-Learnablecited by 290
  7. 2019Towards Efficient Data Valuation Based on the Shapley Valuecited by 279
  8. 2020Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challengescited by 120
  9. 2020Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mappingcited by 102
  10. 2018Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Costcited by 79
  11. 2018GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learningcited by 77
  12. 2019A review on Deep Reinforcement Learning for Fluid Mechanicscited by 65
12 more
  1. 2021Shapley values for feature selection: The good, the bad, and the axiomscited by 54
  2. 2019Simulation-based reinforcement learning for real-world autonomous drivingcited by 51
  3. 2020Correspondence Learning via Linearly-invariant Embeddingcited by 48
  4. 2017Simple and Effective Dimensionality Reduction for Word Embeddingscited by 38
  5. 2021Towards Tight Bounds on the Sample Complexity of Average-reward MDPscited by 32
  6. 2019Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Targetcited by 31
  7. 2019A Human-Grounded Evaluation of SHAP for Alert Processingcited by 23
  8. 2015Giraffe: Using Deep Reinforcement Learning to Play Chesscited by 11
  9. 2018Goal-Oriented Chatbot Dialog Management Bootstrapping with Transfer Learningcited by 11
  10. 2018Deep Bayesian Trust : A Dominant and Fair Incentive Mechanism for Crowdcited by 5
  11. 2019Reinforcement Learning with Non-uniform State Representations for Adaptive Searchcited by 2
  12. 2020Wide Area Measurement System-based Low Frequency Oscillation Damping Control through Reinforcement Learningcited by 2

Built on by

Not cited yet.