Parallel Reinforcement Learning Simulation for Visual Quadrotor Navigation
Not on the map. Why?
Abstract (arXiv)
Reinforcement learning (RL) is an agent-based approach for teaching robots to navigate within the physical world. Gathering data for RL is known to be a laborious task, and real-world experiments can be risky. Simulators facilitate the collection of training data in a quicker and more cost-effective manner. However, RL frequently requires a significant number of simulation steps for an agent to become skilful at simple tasks. This is a prevalent issue within the field of RL-based visual quadrotor navigation where state dimensions are typically very large and dynamic models are complex. Furthermore, rendering images and obtaining physical properties of the agent can be computationally expensive. To solve this, we present a simulation framework, built on AirSim, which provides efficient parallel training. Building on this framework, Ape-X is modified to incorporate decentralised training of AirSim environments to make use of numerous networked computers. Through experiments we were able to achieve a reduction in training time from 3.9 hours to 11 minutes using the aforementioned framework and a total of 74 agents and two networked computers. Further details including a github repo and videos about our project, PRL4AirSim, can be found at https://sites.google.com/view/prl4airsim/home
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 39 references that are in the map. First posted on arXiv 22 Sep 2022.
Builds on
22 of 39 references.
References · 22
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
- 2015Prioritized Experience Replaycited by 1,070
- 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
- 2017A Distributional Perspective on Reinforcement Learningcited by 743
- 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
- 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 517
- 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
- 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
- 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
- 2018Distributed Prioritized Experience Replaycited by 260
- 2018Unity: A General Platform for Intelligent Agentscited by 232
10 more
- 2021Learning High-Speed Flight in the Wildcited by 98
- 2018GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learningcited by 77
- 2020Flightmare: A Flexible Quadrotor Simulatorcited by 69
- 2021Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Controlcited by 68
- 2021Autonomous Drone Racing with Deep Reinforcement Learningcited by 51
- 2019PyRep: Bringing V-REP to Deep Robot Learningcited by 43
- 2016Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Searchcited by 25
- 2018Memory-based Deep Reinforcement Learning for Obstacle Avoidance in UAV with Limited Environment Knowledgecited by 21
- 2021Autonomous Aerial Delivery Vehicles, a Survey of Techniques on how Aerial Package Delivery is Achievedcited by 4
- 2020Deep Reinforcement Learning based Local Planner for UAV Obstacle Avoidance using Demonstration Datacited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.