We present Megaverse, a new 3D simulation platform for reinforcement learning and embodied AI research. The efficient design of our engine enables physics-based simulation with high-dimensional egocentric observations at more than 1,000,000 actions p
er second on a single 8-GPU node. Megaverse is up to 70x faster than DeepMind Lab in fully-shaded 3D scenes with interactive objects. We achieve this high simulation performance by leveraging batched simulation, thereby taking full advantage of the massive parallelism of modern GPUs. We use Megaverse to build a new benchmark that consists of several single-agent and multi-agent tasks covering a variety of cognitive challenges. We evaluate model-free RL on this benchmark to provide baselines and facilitate future research. The source code is available at https://www.megaverse.info
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.
PointGoal navigation has seen significant recent interest and progress, spurred on by the Habitat platform and associated challenge. In this paper, we study PointGoal navigation under both a sample budget (75 million frames) and a compute budget (1 G
PU for 1 day). We conduct an extensive set of experiments, cumulatively totaling over 50,000 GPU-hours, that let us identify and discuss a number of ostensibly minor but significant design choices -- the advantage estimation procedure (a key component in training), visual encoder architecture, and a seemingly minor hyper-parameter change. Overall, these design choices to lead considerable and consistent improvements over the baselines present in Savva et al. Under a sample budget, performance for RGB-D agents improves 8 SPL on Gibson (14% relative improvement) and 20 SPL on Matterport3D (38% relative improvement). Under a compute budget, performance for RGB-D agents improves by 19 SPL on Gibson (32% relative improvement) and 35 SPL on Matterport3D (220% relative improvement). We hope our findings and recommendations will make serve to make the communitys experiments more efficient.
We introduce a learning-based approach for room navigation using semantic maps. Our proposed architecture learns to predict top-down belief maps of regions that lie beyond the agents field of view while modeling architectural and stylistic regulariti
es in houses. First, we train a model to generate amodal semantic top-down maps indicating beliefs of location, size, and shape of rooms by learning the underlying architectural patterns in houses. Next, we use these maps to predict a point that lies in the target room and train a policy to navigate to the point. We empirically demonstrate that by predicting semantic maps, the model learns common correlations found in houses and generalizes to novel environments. We also demonstrate that reducing the task of room navigation to point navigation improves the performance further.
PointGoal Navigation is an embodied task that requires agents to navigate to a specified point in an unseen environment. Wijmans et al. showed that this task is solvable but their method is computationally prohibitive, requiring 2.5 billion frames an
d 180 GPU-days. In this work, we develop a method to significantly increase sample and time efficiency in learning PointNav using self-supervised auxiliary tasks (e.g. predicting the action taken between two egocentric observations, predicting the distance between two observations from a trajectory,etc.).We find that naively combining multiple auxiliary tasks improves sample efficiency,but only provides marginal gains beyond a point. To overcome this, we use attention to combine representations learnt from individual auxiliary tasks. Our best agent is 5.5x faster to reach the performance of the previous state-of-the-art, DD-PPO, at 40M frames, and improves on DD-PPOs performance at 40M frames by 0.16 SPL. Our code is publicly available at https://github.com/joel99/habitat-pointnav-aux.
Recent advances in deep reinforcement learning require a large amount of training data and generally result in representations that are often over specialized to the target task. In this work, we present a methodology to study the underlying potentia
l causes for this specialization. We use the recently proposed projection weighted Canonical Correlation Analysis (PWCCA) to measure the similarity of visual representations learned in the same environment by performing different tasks. We then leverage our proposed methodology to examine the task dependence of visual representations learned on related but distinct embodied navigation tasks. Surprisingly, we find that slight differences in task have no measurable effect on the visual representation for both SqueezeNet and ResNet architectures. We then empirically demonstrate that visual representations learned on one task can be effectively transferred to a different task.
We present Decentralized Distributed Proximal Policy Optimization (DD-PPO), a method for distributed reinforcement learning in resource-intensive simulated environments. DD-PPO is distributed (uses multiple machines), decentralized (lacks a centraliz
ed server), and synchronous (no computation is ever stale), making it conceptually simple and easy to implement. In our experiments on training virtual robots to navigate in Habitat-Sim, DD-PPO exhibits near-linear scaling -- achieving a speedup of 107x on 128 GPUs over a serial implementation. We leverage this scaling to train an agent for 2.5 Billion steps of experience (the equivalent of 80 years of human experience) -- over 6 months of GPU-time training in under 3 days of wall-clock time with 64 GPUs. This massive-scale training not only sets the state of art on Habitat Autonomous Navigation Challenge 2019, but essentially solves the task --near-perfect autonomous navigation in an unseen environment without access to a map, directly from an RGB-D camera and a GPS+Compass sensor. Fortuitously, error vs computation exhibits a power-law-like distribution; thus, 90% of peak performance is obtained relatively early (at 100 million steps) and relatively cheaply (under 1 day with 8 GPUs). Finally, we show that the scene understanding and navigation policies learned can be transferred to other navigation tasks -- the analog of ImageNet pre-training + task-specific fine-tuning for embodied AI. Our model outperforms ImageNet pre-trained CNNs on these transfer tasks and can serve as a universal resource (all models and code are publicly available).
