def __init__(self, env_name, actor_id, logdir="results/", start=True):
env = create_env(env_name)
self.id = actor_id
num_actions = env.action_space.n
self.policy = LSTMPolicy(env.observation_space.shape, num_actions,
actor_id)
self.runner = RunnerThread(env, self.policy, 20)
self.env = env
self.logdir = logdir
if start:
self.start()
def train(num_workers, env_name="PongDeterministic-v3"):
env = create_env(env_name, None, None)
policy = LSTMPolicy(env.observation_space.shape, env.action_space.n, 0)
agents = [Runner(env_name, i) for i in range(num_workers)]
parameters = policy.get_weights()
gradient_list = [agent.compute_gradient(parameters) for agent in agents]
steps = 0
obs = 0
while True:
done_id, gradient_list = ray.wait(gradient_list)
gradient, info = ray.get(done_id)[0]
policy.model_update(gradient)
parameters = policy.get_weights()
steps += 1
obs += info["size"]
gradient_list.extend([agents[info["id"]].compute_gradient(parameters)])
return policy