saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-07-03 03:59:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add tensorboard_log dummy arg

Browse source
This commit is contained in:
Antonin Raffin 2019-10-14 11:09:22 +02:00
parent b5656531d1
commit ab64ff464e
3 changed files with 8 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
torchy_baselines/cem_rl/cem_rl.py
View file

@ -15,13 +15,14 @@ class CEMRL(TD3):
Code: https://github.com/apourchot/CEM-RL
"""
def __init__(self, policy, env, policy_kwargs=None, verbose=0,
sigma_init=1e-3, pop_size=10, damp=1e-3, damp_limit=1e-5,
elitism=False, n_grad=5, policy_delay=2, batch_size=100,
buffer_size=int(1e6), learning_rate=1e-3, seed=0, device='auto',
def __init__(self, policy, env, sigma_init=1e-3, pop_size=10,
damp=1e-3, damp_limit=1e-5, elitism=False, n_grad=5,
policy_delay=2, batch_size=100,
buffer_size=int(1e6), learning_rate=1e-3,
action_noise=None, learning_starts=100, tau=0.005,
n_episodes_rollout=1, update_style='original',
create_eval_env=False,
tensorboard_log=None, create_eval_env=False,
policy_kwargs=None, verbose=0, seed=0, device='auto',
_init_setup_model=True):
super(CEMRL, self).__init__(policy, env,

2
torchy_baselines/sac/sac.py
View file

@ -57,7 +57,7 @@ class SAC(BaseRLModel):
tau=0.005, ent_coef='auto', target_update_interval=1,
train_freq=1, gradient_steps=1, n_episodes_rollout=-1,
target_entropy='auto', action_noise=None,
gamma=0.99, create_eval_env=False,
gamma=0.99, tensorboard_log=None, create_eval_env=False,
policy_kwargs=None, verbose=0, seed=0, device='auto',
_init_setup_model=True):

2
torchy_baselines/td3/td3.py
View file

@ -50,7 +50,7 @@ class TD3(BaseRLModel):
policy_delay=2, learning_starts=100, gamma=0.99, batch_size=100,
train_freq=-1, gradient_steps=-1, n_episodes_rollout=1,
tau=0.005, action_noise=None, target_policy_noise=0.2, target_noise_clip=0.5,
create_eval_env=False, policy_kwargs=None, verbose=0,
tensorboard_log=None, create_eval_env=False, policy_kwargs=None, verbose=0,
seed=0, device='auto', _init_setup_model=True):
super(TD3, self).__init__(policy, env, TD3Policy, policy_kwargs, verbose, device,