wassname 0de68133cf ddpg with a dynamics model ...

I'm trying a dynamics model to provide additional supervision. I'm using
this repo because it's performance tested on a competition and is in
pytorch. I'm intially testing with pendulum. Code is messy as it's a one
time experiment.

2018-01-18 16:41:20 +08:00

..

modules

pytorch version

2017-11-15 22:18:46 +03:00

__init__.py

pytorch version

2017-11-15 22:18:46 +03:00

buffers.py

pytorch version

2017-11-15 22:18:46 +03:00

env_wrappers.py

ddpg with a dynamics model

2018-01-18 16:41:20 +08:00

loss.py

pytorch version

2017-11-15 22:18:46 +03:00

misc_util.py

pytorch version

2017-11-15 22:18:46 +03:00

nets.py

pytorch version

2017-11-15 22:18:46 +03:00

random_process.py

pytorch version

2017-11-15 22:18:46 +03:00

segment_tree.py

pytorch version

2017-11-15 22:18:46 +03:00

state_transform.py

pytorch version

2017-11-15 22:18:46 +03:00

torch_util.py

pytorch version

2017-11-15 22:18:46 +03:00