mlsanityData to 14 Oct 2026

Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning

arXiv 1702.06054 ↗First posted 20 Feb 2017cs.LG cs.AI cs.NEcited by 39

Not on the map. Why?

Abstract (arXiv)

Reinforcement Learning algorithms can learn complex behavioral patterns for sequential decision making tasks wherein an agent interacts with an environment and acquires feedback in the form of rewards sampled from it. Traditionally, such algorithms make decisions, i.e., select actions to execute, at every single time step of the agent-environment interactions. In this paper, we propose a novel framework, Fine Grained Action Repetition (FiGAR), which enables the agent to decide the action as well as the time scale of repeating it. FiGAR can be used for improving any Deep Reinforcement Learning algorithm which maintains an explicit policy estimate by enabling temporal abstractions in the action space. We empirically demonstrate the efficacy of our framework by showing performance improvements on top of three policy search algorithms in different domains: Asynchronous Advantage Actor Critic in the Atari 2600 domain, Trust Region Policy Optimization in Mujoco domain and Deep Deterministic Policy Gradients in the TORCS car racing domain.

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 5; 2024: 9; 2025: 8; 2026: 7.

39 papers.

Sort:

By area:

  1. 2021TempoRL: Learning When to Actcited by 25
  2. 2025Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agentscited by 20
  3. 2021An Analysis of Frame-skipping in Reinforcement Learningcited by 18
  4. 2024On the Brittle Foundations of ReAct Prompting for Agentic Large Language Modelscited by 17
  5. 2022Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rulescited by 16
  6. 2025Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returnscited by 16
  7. 2022Dynamic Decision Frequency with Continuous Optionscited by 13
  8. 2022Generative Planning for Temporally Coordinated Exploration in Reinforcement Learningcited by 10
  9. 2024When to Sense and Control? A Time-adaptive Approach for Continuous-Time RLcited by 9
  10. 2023Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomycited by 6
  11. 2024Deployable Reinforcement Learning with Variable Control Ratecited by 5
  12. 2021Online reinforcement learning with sparse rewards through an active inference capsulecited by 3
27 more
  1. 2023Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learningcited by 3
  2. 2023Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learningcited by 3
  3. 2024Learning Uncertainty-Aware Temporally-Extended Actionscited by 3
  4. 2024Reinforcement Learning with Elastic Time Stepscited by 3
  5. 2025Toward Agents That Reason About Their Computationcited by 3
  6. 2021Reinforcement Learning for Robot Navigation with Adaptive Forward Simulation Time (AFST) in a Semi-Markov Modelcited by 2
  7. 2022Simultaneously Updating All Persistence Values in Reinforcement Learningcited by 2
  8. 2023Speeding-up Evolutionary Algorithms to solve Black-Box Optimization Problemscited by 2
  9. 2024MOSEAC: Streamlined Variable Time Step Reinforcement Learningcited by 2
  10. 2025OptionZero: Planning with Learned Optionscited by 2
  11. 2022Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-offcited by 1
  12. 2022Temporally Layered Architecture for Adaptive, Distributed and Continuous Controlcited by 1
  13. 2023Actor-Critic with variable time discretization via sustained actionscited by 1
  14. 2024State-Novelty Guided Action Persistence in Deep Reinforcement Learningcited by 1
  15. 2024Reinforcement learning to learn quantum states for Heisenberg scaling accuracycited by 1
  16. 2025TARC: Time-Adaptive Robotic Controlcited by 1
  17. 2026When to Plan: Learning to Select Between Reactive Control and Deliberative Planningcited by 1
  18. 2026Let it Cook: Learning to Wait in Sequential Decision Makingcited by 1
  19. 2024Variable Time Step Reinforcement Learning for Robotic Applicationscited by 0
  20. 2025Increasing Information for Model Predictive Control with Semi-Markov Decision Processescited by 0
  21. 2025Select before Act: Spatially Decoupled Action Repetition for Continuous Controlcited by 0
  22. 2025Improving planning and MBRL with temporally-extended actionscited by 0
  23. 2026Online Action-Stacking Improves Reinforcement Learning Performance for Air Traffic Controlcited by 0
  24. 2026When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoningcited by 0
  25. 2026Temporal Self-Imitation Learningcited by 0
  26. 2026Lambda-Hold Control: Human-Like Movement Emerges from a Minimal Task Reward in Predictive Musculoskeletal Simulationcited by 0
  27. 2026Action Chunking Proximal Policy Optimization with Feedback Correctioncited by 0