Link:https://github.com/openai/multiagent-particle-envs 简称小球环境,也是MADDPG用的环境,基本上可以看做是较为复杂的 gridworld 的环境。 在这个环境涵盖了ma里的竞争/协作/通讯场景,你可以根据你的需要设置agent的数量,选择他们要完成的任务,比如合作进行相互抓捕,碰撞等,你也可以继承某一个环境来改写自己的任...
Cancel Submit feedback Saved searches Use saved searches to filter your results more quickly Cancel Create saved search Sign in Sign up Reseting focus {{ message }} openai / multiagent-particle-envs Public Notifications You must be signed in to change notification settings Fork 784 ...
./multiagent/scenario.py: contains base scenario object that is extended for all scenarios. ./multiagent/scenarios/: folder where various scenarios/ environments are stored. scenario code consists of several functions: make_world(): creates all of the entities that inhabit the world (landmarks,...
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments" - multiagent-particle-envs/multiagent/environment.py at master · openai/multiagent-particle-envs
Multi-Agent Particle Environment A simple multi-agent particle world with a continuous observation and discrete action space, along with some basic simulated physics. Used in the paper Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. Getting started: To install, cd into the roo...
class Agent(Entity): def __init__(self): super(Agent, self).__init__() # agents are movable by default self.movable = True # cannot send communication signals self.silent = False # 可以通信 # cannot observe the world self.blind = False ...
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments" - openai/multiagent-particle-envs
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments" - multiagent-particle-envs/multiagent/core.py at master · openai/multiagent-particle-envs
The problem of prng is that the gym package is updating, and prng function has been deleted. you can fix this in code multiagent-particle-envs/multiagent/multi_discrete.py import gym # from gym.spaces import prng # this prng has been can...
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments" - openai/multiagent-particle-envs