import logging
import gym
from agents.SimulatedAnnealing import SimulatedAnnealingAgent


def main():
    logger = logging.getLogger()
    logger.setLevel(logging.DEBUG)

    env = gym.make('Acrobot-v0')

    agent = SimulatedAnnealingAgent(env.action_space, decay=0.8, alpha=3)
    upload = True  # Sets whether to upload to OpenAI

    outdir = '/tmp/' + agent.name + '-results'
    env.monitor.start(outdir, force=True)

    episode_count = 1000

    for i in xrange(episode_count):
        ob = env.reset()
        done = False
        reward = 0

        while not done:
            action = agent.act(ob, reward, done)
            ob, reward, done, _ = env.step(action)

        agent.act(ob, reward, done)    # Final push required so agent receives notification that episode is done and can update model

    # Dump result info to disk
    env.monitor.close()

if __name__ == '__main__':
    main()