Real-Time Physics Simulation Forum 2019-08-11T21:49:24+00:00 https://pybullet.org/Bullet/phpBB3/app.php/feed/topic/12738 2019-08-11T21:49:24+00:00 2019-08-11T21:49:24+00:00 https://pybullet.org/Bullet/phpBB3/viewtopic.php?p=42312#p42312 <![CDATA[reinforcement learning train_ppo]]>
I am trying to run the ppo training example as in the quick start guide
python -m pybullet_envs.agents.train_ppo --config=pybullet_ant --logdir=ant

the train_ppo seems work, but the result policy network does not do anything when tested it with visualize_ppo. anybody have
a working case recently? or there is another forum for this topic?

I am using ubuntu 18, with conda 4.7 and python 3.7. pybullet 2.5.3.

thanks!
J.W

Statistics: Posted by vsurobotics2 — Sun Aug 11, 2019 9:49 pm

]]>