# Large Batch Simulation for Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2103.07013 · HTML: https://mlsanity.com/paper/2103.07013/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 12 Mar 2021.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [Transporter Networks: Rearranging the Visual World for Robotic Manipulation](https://mlsanity.com/paper/2010.14406/) (2020)
- [Distributed Prioritized Experience Replay](https://mlsanity.com/paper/1803.00933/) (2018)
- [ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation](https://mlsanity.com/paper/2007.04954/) (2020)
- [Fixup Initialization: Residual Learning Without Normalization](https://mlsanity.com/paper/1901.09321/) (2019)
- [ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning](https://mlsanity.com/paper/1605.02097/) (2016)
- [TResNet: High Performance GPU-Dedicated Architecture](https://mlsanity.com/paper/2003.13630/) (2020)
- [Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning](https://mlsanity.com/paper/2006.11751/) (2020)
- [Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environments](https://mlsanity.com/paper/1910.14442/) (2019)
- [IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks](https://mlsanity.com/paper/1911.07246/) (2019)
- [MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments](https://mlsanity.com/paper/1712.03931/) (2017)
- [Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes](https://mlsanity.com/paper/1807.11205/) (2018)

## Built on by (most cited first, 19 of 19)

- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation](https://mlsanity.com/paper/2202.02440/) (2022)
- [Robust Autonomy Emerges from Self-Play](https://mlsanity.com/paper/2502.03349/) (2025)
- [XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX](https://mlsanity.com/paper/2312.12044/) (2023)
- [Is Mapping Necessary for Realistic PointGoal Navigation?](https://mlsanity.com/paper/2206.00997/) (2022)
- [CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation](https://mlsanity.com/paper/2311.01447/) (2023)
- [Megaverse: Simulating Embodied Agents at One Million Experiences per Second](https://mlsanity.com/paper/2107.08170/) (2021)
- [VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement](https://mlsanity.com/paper/2210.05064/) (2022)
- [Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey](https://mlsanity.com/paper/2411.05614/) (2024)
- [Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second](https://mlsanity.com/paper/2306.07552/) (2023)
- [Investigating Navigation Strategies in the Morris Water Maze through Deep Reinforcement Learning](https://mlsanity.com/paper/2306.01066/) (2023)
- [Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck](https://mlsanity.com/paper/2109.08677/) (2021)
- [Landmark Policy Optimization for Object Navigation Task](https://mlsanity.com/paper/2109.09512/) (2021)
- [Optimizing Data Collection in Deep Reinforcement Learning](https://mlsanity.com/paper/2207.07736/) (2022)
- [Simulation and application of COVID-19 compartment model using physics-informed neural network](https://mlsanity.com/paper/2208.02433/) (2022)
- [PyBatchRender: A Python Library for Batched 3D Rendering at Up to One Million FPS](https://mlsanity.com/paper/2601.01288/) (2026)
- [Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training](https://mlsanity.com/paper/2604.26833/) (2026)
- [FlashNav: Training Deployable Robot Navigation Policies in Seconds](https://mlsanity.com/paper/2606.15846/) (2026)

## Abstract (arXiv)

We accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work, realizing end-to-end training speeds of over 19,000 frames of experience per second on a single GPU and up to 72,000 frames per second on a single eight-GPU machine. The key idea of our approach is to design a 3D renderer and embodied navigation simulator around the principle of "batch simulation": accepting and executing large batches of requests simultaneously. Beyond exposing large amounts of work at once, batch simulation allows implementations to amortize in-memory storage of scene assets, rendering work, data loading, and synchronization costs across many simulation requests, dramatically improving the number of simulated agents per GPU and overall simulation throughput. To balance DNN inference and training costs with faster simulation, we also build a computationally efficient policy DNN that maintains high task performance, and modify training algorithms to maintain sample efficiency when training with large mini-batches. By combining batch simulation and DNN performance optimizations, we demonstrate that PointGoal navigation agents can be trained in complex 3D environments on a single GPU in 1.5 days to 97% of the accuracy of agents trained on a prior state-of-the-art system using a 64-GPU cluster over three days. We provide open-source reference implementations of our batch 3D renderer and simulator to facilitate incorporation of these ideas into RL systems.