Automatic labelling game objects visible in the frame,.Access to the depth buffer (3D vision),.Customizable resolution and rendering parameters,.Fast (up to 7000 fps in sync mode, single-threaded),.Async and sync single-player and multi-player modes,.Easy-to-create custom scenarios (visual editors, scripting language and examples available),.OpenAI Gym environment wrappers for basic scenarios.API for Python, C++, and Julia (thanks to Jun Tian), and also Lua and Java for older versions,.Multi-platform (Linux, macOS, Windows),.ViZDoom is based on ZDoom to provide the game mechanics. ![]() It is primarily intended for research in machine visual learning, and deep reinforcement learning, in particular. ViZDoom allows developing AI bots that play Doom using only the visual information (the screen buffer).
0 Comments
Leave a Reply. |