Erwin Coumans
|
8e8955571f
|
workaround for Tensorflow 2.x breaking API:
try:
import tensorflow.compat.v1 as tf
except Exception:
import tensorflow as tf
|
2020-02-29 20:35:05 -08:00 |
|
Rodrigo Queiro
|
d18531cc6a
|
Replace tensorflow with tf.compat.v1
This means they won't break when using TensorFlow 2.0.
|
2020-02-19 17:35:48 +01:00 |
|
Erwin Coumans
|
528bd28e34
|
increase plane from 30 to 200 (to allow quadrupeds to run further, not fall off cliff)
fix issue with gym.wrappers in pybullet_envs.agents.visualize_ppo.py
|
2019-12-31 18:13:49 -08:00 |
|
Erwin Coumans
|
ef9570c315
|
add yapf style and apply yapf to format all Python files
This recreates pull request #2192
|
2019-04-27 07:31:15 -07:00 |
|
Erwin Coumans
|
7b030426c1
|
add a temp copy of TF agents (until the API stops changing or configs.py are included)
|
2017-11-16 16:47:14 +00:00 |
|
Erwin Coumans
|
d18bfec1a9
|
API changes in TensorFlow Agents
See 164f620326 (diff-82bda908f176861c20aadc1d017c2527)
|
2017-10-20 20:32:49 -07:00 |
|
Erwin Coumans
|
345836d670
|
revert to original agents train/visualize scripts, but using pybullet envs in configs.py (agents lacks a convenient way to extend environments)
|
2017-09-28 10:19:41 -07:00 |
|
Erwin Coumans
|
e4a3b3fe38
|
add TensorFlow Agents PPO training script for various pybullet environments:
example:
python -m pybullet_envs.agents.train_ppo --config=pybullet_pendulum --logdir=pendulum
|
2017-09-27 10:20:38 -07:00 |
|