Files
baselines/baselines/acktr/run_mujoco.py
John Schulman 9fa8e1baf1 Lots of cleanups
Fixes for new gym version
Add @olegklimov and @unixpickle to authors list
2018-01-25 18:54:24 -08:00

35 lines
1.1 KiB
Python

#!/usr/bin/env python3
import tensorflow as tf
from baselines import logger
from baselines.common.cmd_util import make_mujoco_env, mujoco_arg_parser
from baselines.acktr.acktr_cont import learn
from baselines.acktr.policies import GaussianMlpPolicy
from baselines.acktr.value_functions import NeuralNetValueFunction
def train(env_id, num_timesteps, seed):
env = make_mujoco_env(env_id, seed)
with tf.Session(config=tf.ConfigProto()):
ob_dim = env.observation_space.shape[0]
ac_dim = env.action_space.shape[0]
with tf.variable_scope("vf"):
vf = NeuralNetValueFunction(ob_dim, ac_dim)
with tf.variable_scope("pi"):
policy = GaussianMlpPolicy(ob_dim, ac_dim)
learn(env, policy=policy, vf=vf,
gamma=0.99, lam=0.97, timesteps_per_batch=2500,
desired_kl=0.002,
num_timesteps=num_timesteps, animate=False)
env.close()
def main():
args = mujoco_arg_parser().parse_args()
logger.configure()
train(args.env, num_timesteps=args.num_timesteps, seed=args.seed)
if __name__ == "__main__":
main()