How to continue training a model with train_ppo ?

Official Python bindings with a focus on reinforcement learning and robotics.
Post Reply
underactuated
Posts: 1
Joined: Tue Jul 24, 2018 7:45 pm

How to continue training a model with train_ppo ?

Post by underactuated » Tue Jul 24, 2018 8:05 pm

I trained a model in the pybullet_ant environment with

python -m pybullet_envs.agents.train_ppo --config=pybullet_ant --logdir=ant

The trained model is now stored in ant/xxxxx (where xxxxx is a time-stamped subdirectory). Can I force train_ppo to load the trained model in a new training session? So I would continue training it, instead of starting from scratch?

Thank you.

Post Reply