mlsanityData to 14 Oct 2026

Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems

arXiv 2607.10309 ↗First posted 11 Jul 2026cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT). However, the trial-and-error nature of RL, when conducted in real-world environments, is costly and hazardous in some scenarios. Consequently, the majority of RL research is conducted in simulation. This reliance introduces challenges related to the Sim-to-Real transferability. Evaluating the Sim-to-Real algorithmic robustness and the Sim-to-Real gap is a critical prerequisite for research aimed at improving RL performance in the real world. Therefore, industries such as robotics have developed concurrent simulation and physical platforms to facilitate this research. However, a universal Sim-to-Real benchmark platform for AIoT does not currently exist. To address these concerns, we developed a real-world AIoT platform for studying RL in AIoT. On this platform, an agent deployed on an edge device plays video games on a separate host computer via a hardware-emulated keyboard, guided by vision input. This platform uses commercially available components costing less than USD 400, together with two computers. Because the system's objective is game score maximization, it inherently mitigates safety risks associated with real-world RL deployments. Experimental results show the simulation-trained agent suffers a 1160% performance degradation relative to the human-level performance after real-world deployment, indicating a significant Sim-to-Real gap. Direct real-world training using the deep Q-network (DQN) algorithm achieves approximately 49% of human-level performance after 10 million training steps, demonstrating the feasibility of RL under real-world conditions. These results suggest that the proposed Sim-to-Real benchmark platform provides a substantial foundation for qualitative and quantitative evaluations of RL in real-world AIoT systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 45 references that are in the map. First posted on arXiv 11 Jul 2026.

Builds on

17 of 45 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots29 May
  2. 2024Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL26 Oct

Other references · 15

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  6. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  7. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  8. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  9. 2018Learning Dexterous In-Hand Manipulationcited by 687
  10. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
  11. 2017Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agentscited by 269
  12. 2019Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challengescited by 37
3 more
  1. 2019Deep Reinforcement Learning for Smart Home Energy Managementcited by 30
  2. 2024CALE: Continuous Arcade Learning Environmentcited by 5
  3. 2023Exploring Deep Reinforcement Learning for Holistic Smart Building Controlcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Revealing the Challenges of Sim-to-Real Transfer in Model-Based Reinforcement Learning via Latent Space Modeling
  2. 2025A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models
  3. 2025Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning
  4. 2025SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training
  5. 2026The Open Ant: A Robot Platform for Reinforcement Learning Research
  6. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey
  7. 2025A2Perf: Real-World Autonomous Agents Benchmark
  8. 2025Sim-to-Real Transfer for Mobile Robots with Reinforcement Learning: from NVIDIA Isaac Sim to Gazebo and Real ROS 2 Robots