def run(env):
from lola.train_pg import train
train(env,
num_episodes=num_episodes,
trace_length=trace_length,
batch_size=batch_size,
gamma=gamma,
lr=lr,
lr_correction=lr_correction,
corrections=lola,
simple_net=simple_net,
hidden=hidden)
def run(env):
from lola.train_pg import train
train(env,
num_episodes=num_episodes,
trace_length=trace_length,
batch_size=batch_size,
gamma=gamma,
set_zero=0,
lr=lr,
corrections=lola,
simple_net=simple_net,
hidden=hidden,
mem_efficient=mem_efficient)
def run(env):
from lola.train_exact import train
train(env,
num_episodes=num_episodes,
trace_length=trace_length,
simple_net=simple_net,
corrections=lola,
pseudo=pseudo,
num_hidden=hidden,
reg=reg,
lr=lr,
lr_correction=lr_correction,
gamma=gamma)
def run(env):
from lola.train_cg import train
train(env,
num_episodes=num_episodes,
trace_length=trace_length,
batch_size=batch_size,
bs_mul=bs_mul,
gamma=gamma,
grid_size=grid_size,
lr=lr,
corrections=lola,
opp_model=opp_model,
hidden=hidden,
mem_efficient=mem_efficient)
def run(env):
from lola.train_cg_le import train
train(env,
num_episodes=num_episodes,
trace_length=trace_length,
batch_size=batch_size,
bs_mul=bs_mul,
gamma=gamma,
grid_size=grid_size,
lr=lr,
corrections=lola,
opp_model=opp_model,
hidden=hidden,
welfare0=welfare_fn0,
welfare1=welfare_fn1,
punish=True,
mem_efficient=mem_efficient)