adaa8aefa8
* fixes to enjoy_cartpole, enjoy_mountaincar.py
* fixed {train,enjoy}_pong, removed enjoy_retro
* set number of timesteps to 1e7 in train_pong
* flake8 complaints
* use synchronous version fo acktr in test_env_after_learn
* flake8
22 lines
486 B
Python
22 lines
486 B
Python
import gym
|
|
|
|
from baselines import deepq
|
|
|
|
|
|
def main():
|
|
env = gym.make("CartPole-v0")
|
|
act = deepq.learn(env, network='mlp', total_timesteps=0, load_path="cartpole_model.pkl")
|
|
|
|
while True:
|
|
obs, done = env.reset(), False
|
|
episode_rew = 0
|
|
while not done:
|
|
env.render()
|
|
obs, rew, done, _ = env.step(act(obs[None])[0])
|
|
episode_rew += rew
|
|
print("Episode reward", episode_rew)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|