We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
"return_mean" value remains constant value = 45.0 in all steps in metric.json with COMA or MAA2C. but why?
class ClassName(MultiAgentEnv): def init(self): self.n_agents = 10 self.observation_space = gym.spaces.Tuple(tuple( [gym.spaces.Box(np.array([0,0,0,0,0,0,0,0,0,0]), np.array([3,108,6,8,3,2,3,17,19,17]), shape=(10,), dtype=np.int64)] * self.n_agents )) self.action_space = gym.spaces.Tuple(tuple([ gym.spaces.Discrete(4), gym.spaces.Discrete(109), gym.spaces.Discrete(7), gym.spaces.Discrete(9), gym.spaces.Discrete(4), gym.spaces.Discrete(3), gym.spaces.Discrete(4), gym.spaces.Discrete(18), gym.spaces.Discrete(20), gym.spaces.Discrete(18) ])) self.state = np.array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0]) self.episode = 0 self.thereshold = -10000 super().init()
def reset(self): self.state = np.array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0]) return self.observation_space.sample() def step(self, actions): cooperation_reward = Compute_reward_function(actions) self.state = actions obs, rew, dones, info = {}, {}, {}, {} for i in range(10): obs[i] = self.observation_space.sample() rew[i] = cooperation_reward dones[i] = False info[i] = {} if(cooperation_reward > self.thereshold): self.thereshold = cooperation_reward dones = self.n_agents * [True] self.episode +=1 dones = self.n_agents * [True] return obs, rew, dones, info
The text was updated successfully, but these errors were encountered:
No branches or pull requests
"return_mean" value remains constant value = 45.0 in all steps in metric.json with COMA or MAA2C. but why?
class ClassName(MultiAgentEnv):
def init(self):
self.n_agents = 10
self.observation_space = gym.spaces.Tuple(tuple( [gym.spaces.Box(np.array([0,0,0,0,0,0,0,0,0,0]),
np.array([3,108,6,8,3,2,3,17,19,17]), shape=(10,), dtype=np.int64)] * self.n_agents ))
self.action_space = gym.spaces.Tuple(tuple([
gym.spaces.Discrete(4),
gym.spaces.Discrete(109),
gym.spaces.Discrete(7),
gym.spaces.Discrete(9),
gym.spaces.Discrete(4),
gym.spaces.Discrete(3),
gym.spaces.Discrete(4),
gym.spaces.Discrete(18),
gym.spaces.Discrete(20),
gym.spaces.Discrete(18)
]))
self.state = np.array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
self.episode = 0
self.thereshold = -10000
super().init()
The text was updated successfully, but these errors were encountered: