Megaverse：以每秒一百万次经验模拟具身智能体
Megaverse: Simulating Embodied Agents at One Million Experiences per Second
摘要：
我们介绍了Megaverse，一个新的3D仿真平台，用于强化学习和具体的AI研究。我们的引擎的高效设计使基于物理的仿真能够在单个8 GPU节点上以每秒超过1，000，000个动作的高维自我中心观察。Megaverse在具有交互式对象的全阴影3D场景中比DeepMind Lab快70倍。我们通过利用批处理模拟来实现这种高模拟性能，从而充分利用现代GPU的大规模并行性。我们使用Megaverse来构建一个新的基准，该基准由几个单智能体和多智能体任务组成，涵盖各种认知挑战。我们在这个基准上评估无模型RL，以提供基线并促进未来的研究。源代码可在https://www.megaverse.info上获得
英文摘要：
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 per 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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
