mlsanityData to 7 Oct 2026

Discrete and Continuous Action Representation for Practical RL in Video Games

arXiv 1912.11077 ↗First posted 23 Dec 2019cs.LG cs.AI stat.MLcited by 34

Not on the map. Why?

Abstract (arXiv)

While most current research in Reinforcement Learning (RL) focuses on improving the performance of the algorithms in controlled environments, the use of RL under constraints like those met in the video game industry is rarely studied. Operating under such constraints, we propose Hybrid SAC, an extension of the Soft Actor-Critic algorithm able to handle discrete, continuous and parameterized actions in a principled way. We show that Hybrid SAC can successfully solve a highspeed driving task in one of our games, and is competitive with the state-of-the-art on parameterized actions benchmark tasks. We also explore the impact of using normalizing flows to enrich the expressiveness of the policy at minimal computational cost, and identify a potential undesired effect of SAC when used with normalizing flows, that may be addressed by optimizing a different objective.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 8; 2022: 7; 2023: 5; 2024: 5; 2025: 3; 2026: 5.

34 papers.

Sort:

By area:

  1. 2021Hierarchical Skills for Efficient Explorationcited by 37
  2. 2021HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representationcited by 33
  3. 2020Benchmarking End-to-End Behavioural Cloning on Video Gamescited by 15
  4. 2021TAAC: Temporally Abstract Actor-Critic for Continuous Controlcited by 14
  5. 2022Monte Carlo Tree Search based Hybrid Optimization of Variational Quantum Circuitscited by 10
  6. 2023Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learningcited by 10
  7. 2021Identifying optimal cycles in quantum thermal machines with reinforcement-learningcited by 6
  8. 2021A Hybrid Approach for Learning to Shift and Grasp with Elaborate Motion Primitivescited by 6
  9. 2021Policy Fusion for Adaptive and Customizable Reinforcement Learning Agentscited by 4
  10. 2021Design Strategy Network: A deep hierarchical framework to represent generative design strategies in complex action spacescited by 4
  11. 2024Robust Imitation Learning for Automated Game Testingcited by 4
  12. 2025Advancing Safe Mechanical Ventilation Using Offline RL With Hybrid Actions and Clinically Aligned Rewardscited by 3
22 more
  1. 2021Soft Actor-Critic With Integer Actionscited by 2
  2. 2022Investigation of Factorized Optical Flows as Mid-Level Representationscited by 2
  3. 2024A learning-based approach to stochastic optimal control under reach-avoid constraintcited by 2
  4. 2026GenAI-Net: A Generative AI Framework for Automated Biomolecular Network Designcited by 2
  5. 2022Model-free optimization of power/efficiency tradeoffs in quantum thermal machines using reinforcement learningcited by 1
  6. 2023Diverse Policy Optimization for Structured Action Spacecited by 1
  7. 2023Virtual Guidance as a Mid-level Representation for Navigation with Augmented Realitycited by 1
  8. 2023Visual Forecasting as a Mid-level Representation for Avoidancecited by 1
  9. 2024Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policiescited by 1
  10. 2024Artificially intelligent Maxwell's demon for optimal control of open quantum systemscited by 1
  11. 2026Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generationcited by 1
  12. 2022Building Decision Forest via Deep Reinforcement Learningcited by 0
  13. 2022Deep Multi-Agent Reinforcement Learning with Hybrid Action Spaces based on Maximum Entropycited by 0
  14. 2022A further exploration of deep Multi-Agent Reinforcement Learning with Hybrid Action Spacecited by 0
  15. 2022Computational Discovery of Energy-Efficient Heat Treatment for Microstructure Design using Deep Reinforcement Learningcited by 0
  16. 2023Position control of an acoustic cavitation bubble by reinforcement learningcited by 0
  17. 2024Scheduling Drone and Mobile Charger via Hybrid-Action Deep Reinforcement Learningcited by 0
  18. 2025Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor Controlcited by 0
  19. 2025FM-EAC: Feature Model-based Enhanced Actor-Critic for Multi-Task Control in Dynamic Environmentscited by 0
  20. 2026Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spacescited by 0
  21. 2026Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26cited by 0
  22. 2026Reinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear Programmingcited by 0