mlsanityData to 7 Oct 2026

Action Space Shaping in Deep Reinforcement Learning

arXiv 2004.00980 ↗First posted 2 Apr 2020cs.AIcited by 45

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) has been successful in training agents in various learning environments, including video-games. However, such work modifies and shrinks the action space from the game's original. This is to avoid trying "pointless" actions and to ease the implementation. Currently, this is mostly done based on intuition, with little systematic research supporting the design decisions. In this work, we aim to gain insight on these action space modifications by conducting extensive experiments in video-game environments. Our results show how domain-specific removal of actions and discretization of continuous actions can be crucial for successful learning. With these insights, we hope to ease the use of RL in new environments, by clarifying what action-spaces are easy to learn.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 6; 2023: 6; 2024: 7; 2025: 12; 2026: 9.

45 papers.

Sort:

By area:

  1. 2021Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networkscited by 38
  2. 2021Gym-μRTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learningcited by 19
  3. 2023Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Gamescited by 10
  4. 2022Automated Reinforcement Learning: An Overviewcited by 9
  5. 2024Embedding-Aligned Language Modelscited by 9
  6. 2023BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Taskscited by 8
  7. 2021Generalising Discrete Action Spaces with Conditional Action Treescited by 6
  8. 2022Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Maskingcited by 6
  9. 2025The Crucial Role of Problem Formulation in Real-World Reinforcement Learningcited by 6
  10. 2024Learning the Optimal Power Flow: Environment Design Matterscited by 5
  11. 2025RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigationcited by 5
  12. 2021Distilling Reinforcement Learning Tricks for Video Gamescited by 3
33 more
  1. 2022Automating DBSCAN via Deep Reinforcement Learningcited by 3
  2. 2023InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Modelscited by 3
  3. 2023Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learningcited by 3
  4. 2024Beyond the Sum: Unlocking AI Agents Potential Through Market Forcescited by 3
  5. 2022Distributional Reinforcement Learning for Scheduling of Chemical Production Processescited by 2
  6. 2022CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collectioncited by 1
  7. 2022Towards Modern Card Games with Large-Scale Action Spaces Through Action Representationcited by 1
  8. 2023LoopTune: Optimizing Tensor Computations with Reinforcement Learningcited by 1
  9. 2025Reinforcement Learning-based Approach for Vehicle-to-Building Charging with Heterogeneous Agents and Long Term Rewardscited by 1
  10. 2025Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learningcited by 1
  11. 2025Adapting Vision-Language Models for Evaluating World Modelscited by 1
  12. 2025Action Space Reduction Strategies for Reinforcement Learning in Autonomous Drivingcited by 1
  13. 2026Neuro-symbolic Action Masking for Deep Reinforcement Learningcited by 1
  14. 2021MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowlcited by 0
  15. 2023Context-Aware Composition of Agent Policies by Markov Decision Process Entity Embeddings and Agent Ensemblescited by 0
  16. 2024Scalable Volt-VAR Optimization using RLlib-IMPALA Framework: A Reinforcement Learning Approachcited by 0
  17. 2024Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learningcited by 0
  18. 2024Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action Spacescited by 0
  19. 2024Applying Action Masking and Curriculum Learning Techniques to Improve Data Efficiency and Overall Performance in Operational Technology Cyber Security using Reinforcement Learningcited by 0
  20. 2025Reducing Action Space for Deep Reinforcement Learning via Causal Effect Estimationcited by 0
  21. 2025Navigating Demand Uncertainty in Container Shipping: Deep Reinforcement Learning for Enabling Adaptive and Feasible Master Stowage Planningcited by 0
  22. 2025To Start Up a Start-Up-Embedding Strategic Demand Development in Operational On-Demand Fulfillment via Reinforcement Learning with Information Shapingcited by 0
  23. 2025A General Approach of Automated Environment Design for Learning the Optimal Power Flowcited by 0
  24. 2025Where to Intervene: Action Selection in Deep Reinforcement Learningcited by 0
  25. 2025Reinforcement learning for graph theory, Parallelizing Wagner's approachcited by 0
  26. 2026Online Action-Stacking Improves Reinforcement Learning Performance for Air Traffic Controlcited by 0
  27. 2026Sim-to-Real Transfer via a Style-Identified Cycle Consistent Generative Adversarial Network: Zero-Shot Deployment on Robotic Manipulators through Visual Domain Adaptationcited by 0
  28. 2026Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Schedulingcited by 0
  29. 2026NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testingcited by 0
  30. 2026Jamming-Resilient PRB Reservation for Latency-Critical O-RAN Network Slicingcited by 0
  31. 2026The Challenges of Using Reinforcement Learning for Controlling Industrial Energy Systemscited by 0
  32. 2026Action Shaping: Policies Absorb What They Can Expresscited by 0
  33. 2026Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Biascited by 0