2 个仓库
Awesome GitHub RepositoriesAgent Behavior Visualizers
Renders top-down maps, agent trajectories, and 3D scene views using off-screen rendering and matplotlib integration.
Distinct from Interactive Visualization Rendering: Distinct from Interactive Visualization Rendering: focuses on visualizing agent behavior and simulation state, not general data chart rendering.
Explore 2 awesome GitHub repositories matching data & databases · Agent Behavior Visualizers. Refine with filters or upvote what's useful.
Awesome Agent Behavior Visualizers GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- ikostrikov/pytorch-a2c-ppo-acktr-gail
ikostrikov/pytorch-a2c-ppo-acktr-gail
3,901在 GitHub 上查看这是一个 PyTorch 强化学习库，专为在模拟环境中训练智能体而设计。它提供了一系列深度强化学习算法，重点关注策略梯度方法和信赖域优化。 该库实现了一套策略梯度算法，包括 A2C 和 PPO，以及一个使用生成对抗模仿学习 (GAIL) 的模仿学习框架。它特别具有 ACKTR 算法的可扩展实现，利用 Kronecker 因子近似来实现高效的信赖域优化。 该代码库涵盖了更广泛的功能，包括用于模拟集成的标准化环境接口、基于经验的批处理，以及用于可视化智能体行为和训练进度的工具。
Provides tools for rendering agent trajectories and 3D scene views in notebooks to evaluate learned policies.
Pythona2cacktractor-critic - facebookresearch/habitat-lab
facebookresearch/habitat-lab
2,848在 GitHub 上查看Habitat-Lab is an open-source platform for training and evaluating embodied AI agents in photorealistic 3D indoor environments. It functions as a high-performance 3D indoor environment simulator that supports physics-based interaction, enabling research into navigation and manipulation tasks. The platform provides a modular task-environment abstraction that separates task logic from environment simulation, using configuration-driven pipeline assembly to compose simulation and training pipelines. It includes a hierarchical sensor-actuator architecture for mixing and matching perception and act
Renders top-down maps, agent trajectories, and 3D scene views using off-screen rendering and matplotlib integration.
Pythonaicomputer-visiondeep-learning
