mlsanityData to 14 Oct 2026

At Human Speed: Deep Reinforcement Learning with Action Delay

arXiv 1810.07286 ↗First posted 16 Oct 2018cs.AI cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of tasks, from video games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning and reinforcement learning, that learn to play from experience with minimal prior knowledge. However, these machines often do not win through intelligence alone -- they possess vastly superior speed and precision, allowing them to act in ways a human never could. To level the playing field, we restrict the machine's reaction time to a human level, and find that standard deep reinforcement learning methods quickly drop in performance. We propose a solution to the action delay problem inspired by human perception -- to endow agents with a neural predictive model of the environment which "undoes" the delay inherent in their environment -- and demonstrate its efficacy against professional players in Super Smash Bros. Melee, a popular console fighting game.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 1; 2022: 3; 2023: 4; 2024: 5; 2025: 5; 2026: 7.

26 papers.

Sort:

By area:

  1. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  2. 2025A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Modelscited by 38
  3. 2021Acting in Delayed Environments with Non-Stationary Markov Policiescited by 31
  4. 2022Delayed Reinforcement Learning by Imitationcited by 16
  5. 2020Benchmarking End-to-End Behavioural Cloning on Video Gamescited by 15
  6. 2023Neural Laplace Control for Continuous-time Delayed Systemscited by 10
  7. 2024Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delayscited by 10
  8. 2024Variational Delayed Policy Optimizationcited by 9
  9. 2023DiAReL: Reinforcement Learning with Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Controlcited by 7
  10. 2024DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delayscited by 7
  11. 2025Handling Delay in Real-Time Reinforcement Learningcited by 7
  12. 2023Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimizationcited by 4
14 more
  1. 2022A Neural Active Inference Model of Perceptual-Motor Learningcited by 2
  2. 2026Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latencycited by 2
  3. 2022Temporally Layered Architecture for Adaptive, Distributed and Continuous Controlcited by 1
  4. 2023Adaptive PD Control using Deep Reinforcement Learning for Local-Remote Teleoperation with Stochastic Time Delayscited by 1
  5. 2024Control in Stochastic Environment with Delays: A Model-based Reinforcement Learning Approachcited by 1
  6. 2025Reinforcement Learning via Conservative Agent for Environments with Random Delayscited by 1
  7. 2026The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspectivecited by 1
  8. 2024Trajectory Planning for Teleoperated Space Manipulators Using Deep Reinforcement Learningcited by 0
  9. 2025Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Delayed Observationcited by 0
  10. 2026Delayed homomorphic reinforcement learning for environments with delayed feedbackcited by 0
  11. 2026Structural Equivalence and Learning Dynamics in Delayed MARLcited by 0
  12. 2026Residual Reinforcement Learning for Robot Teleoperation under Stochastic Delayscited by 0
  13. 2026LangLoc: "Tell Me What You See"cited by 0
  14. 2026Separating Decision Time from Decision Quality in the Real-Time Gap of Distilled Deciders: Evidence from a Game and a Conveyor Simulatorcited by 0