[Examples] Add Carla test env (#1343)

* add carla example

* add reward

* set obs

* Sun Dec 17 16:06:00 PST 2017

* add spec

* fix measurement

* add train script

* resize to 80x80

* null

* initial small training run

* robustify env, clean up action space

* clean up vars

* switch to town2 which is faster

* tunify train.py

* add discrete mode

* update

* fix excessive brakinG

* fix the weather

* rename

* redirect output and from future import

* doc

* update

* fix rebase

* allow dqn gpu growht

* adjust dqn hyperparams

* better ppo parameters
This commit is contained in:
Eric Liang
2017-12-19 12:57:58 -08:00
committed by Philipp Moritz
parent 24b93b1123
commit 6724f57b03
5 changed files with 431 additions and 2 deletions
+1 -2
View File
@@ -216,8 +216,7 @@ class FrameStack(gym.Wrapper):
def wrap_dqn(env, options):
"""Apply a common set of wrappers for DQN."""
is_atari = (hasattr(env.observation_space, "shape") and
env.observation_space.shape == ModelCatalog.ATARI_OBS_SHAPE)
is_atari = hasattr(env.unwrapped, "ale")
if is_atari:
env = EpisodicLifeEnv(env)