File size: 966 Bytes
c223161 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 |
1) model = PPO(policy = "MlpPolicy",
env = env,
n_steps = 1024,
batch_size = 64,
n_epochs = 4,
gamma = 0.999,
gae_lambda = 0.98,
ent_coef = 0.01,
verbose=1)
model.learn(total_timesteps = 500000)
mean_reward=193.60 +/- 21.32519973099738
2) model = PPO(policy = "MlpPolicy",
env = env,
n_steps = 1024,
batch_size = 64,
n_epochs = 8,
gamma = 0.999,
gae_lambda = 0.98,
ent_coef = 0.01,
verbose=1)
model.learn(total_timesteps = 500000)
mean_reward=235.09 +/- 21.878789192117072
3) model = PPO(policy = "MlpPolicy",
env = env,
n_steps = 1024,
batch_size = 64,
n_epochs = 8,
gamma = 0.999,
gae_lambda = 0.98,
ent_coef = 0.01,
verbose=1)
model.learn(total_timesteps = 1000000)
|