brain = env.brains[env.brain_names[0]]
env_info = env.reset(train_mode=True)[env.brain_names[0]]
n_agents = len(env_info.agents)
print('Number of agents:', n_agents)
action_size = brain.vector_action_space_size
state_size = brain.vector_observation_space_size
state_multiplier = brain.num_stacked_vector_observations
action_type = brain.vector_action_space_type
comment = f"MADDPG Unity Tennis"
log_dir = os.path.join('./runs', current_time + '_' + comment)
os.mkdir(log_dir)
print(f"logging to {log_dir}")
writer = SummaryWriter(log_dir=log_dir)
config = DefaultMunch()
config.seed = seed
config.n_episodes = 40000
config.max_t = 1000
config.buffer_size = 100000
config.batch_size = 200
config.gamma = 0.99
config.tau = 0.001
config.lr_actor = 0.0001
config.lr_critic = 0.0001
config.n_agents = n_agents
config.state_size = state_size * state_multiplier
config.action_size = action_size
config.learn_start = 10000
config.max_action = 1 # maximum value allowed for each action
config.memory = ExperienceReplayMemory(config.buffer_size, seed)
config.update_every = 2
config.device = torch.device(
worker_id=worker_id,
seed=seed,
no_graphics=False)
brain = env.brains[env.brain_names[0]]
env_info = env.reset(train_mode=False)[env.brain_names[0]]
n_agents = len(env_info.agents)
print('Number of agents:', n_agents)
action_size = brain.vector_action_space_size
state_size = brain.vector_observation_space_size
state_multiplier = brain.num_stacked_vector_observations
action_type = brain.vector_action_space_type
comment = f"MADDPG Unity Tennis"
rand_seed = 0
config = DefaultMunch()
config.seed = seed
config.n_episodes = 10
config.max_t = 1000
config.buffer_size = 100000
config.batch_size = 200
config.gamma = 0.99
config.tau = 0.001
config.lr_actor = 0.0001
config.lr_critic = 0.001
config.n_agents = n_agents
config.state_size = state_size * state_multiplier
config.action_size = action_size
config.learn_start = 3000
config.max_action = 1
config.memory = ExperienceReplayMemory(config.buffer_size, rand_seed)
config.update_every = 2
config.device = device
