def main():
logger.configure()
env = make_atari('PongNoFrameskip-v4')
env = bench.Monitor(env, logger.get_dir())
env = deepq.wrap_atari_dqn(env)
model = deepq.learn(
env,
"conv_only",
convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
hiddens=[256],
dueling=True,
lr=1e-4,
total_timesteps=int(1e7),
buffer_size=10000,
exploration_fraction=0.1,
exploration_final_eps=0.01,
train_freq=4,
learning_starts=10000,
target_network_update_freq=1000,
gamma=0.99,
)
model.save('pong_model.pkl')
env.close()
def main():
env = gym.make("CartPole-v0")
act = deepq.learn(env,
network='mlp',
lr=1e-3,
total_timesteps=100000,
buffer_size=50000,
exploration_fraction=0.1,
exploration_final_eps=0.02,
print_freq=10,
callback=callback)
print("Saving model to cartpole_model.pkl")
act.save("cartpole_model.pkl")
def main():
env = gym.make("MountainCar-v0")
# Enabling layer_norm here is import for parameter space noise!
act = deepq.learn(env,
network=models.mlp(num_hidden=64, num_layers=1),
lr=1e-3,
total_timesteps=100000,
buffer_size=50000,
exploration_fraction=0.1,
exploration_final_eps=0.1,
print_freq=10,
param_noise=True)
print("Saving model to mountaincar_model.pkl")
act.save("mountaincar_model.pkl")
def main():
env = gym.make("MountainCar-v0")
act = deepq.learn(env,
network=models.mlp(num_layers=1, num_hidden=64),
total_timesteps=0,
load_path='mountaincar_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)
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)
def main():
env = gym.make("PongNoFrameskip-v4")
env = deepq.wrap_atari_dqn(env)
model = deepq.learn(env,
"conv_only",
convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
hiddens=[256],
dueling=True,
total_timesteps=0)
while True:
obs, done = env.reset(), False
episode_rew = 0
while not done:
env.render()
obs, rew, done, _ = env.step(model(obs[None])[0])
episode_rew += rew
print("Episode reward", episode_rew)