move carla example too

Author: ericl

doc/source/rllib-env.rst

@@ -50,7 +50,7 @@ In the above example, note that the ``env_creator`` function takes in an ``env_c
 OpenAI Gym
 ----------
 
-RLlib uses Gym as its environment interface for single-agent training. For more information on how to implement a custom Gym environment, see the `gym.Env class definition <https://github.com/openai/gym/blob/master/gym/core.py>`__. You may also find the `SimpleCorridor <https://github.com/ray-project/ray/blob/master/python/ray/rllib/examples/custom_env.py>`__ and `Carla simulator <https://github.com/ray-project/ray/blob/master/examples/carla/env.py>`__ example env implementations useful as a reference.
+RLlib uses Gym as its environment interface for single-agent training. For more information on how to implement a custom Gym environment, see the `gym.Env class definition <https://github.com/openai/gym/blob/master/gym/core.py>`__. You may also find the `SimpleCorridor <https://github.com/ray-project/ray/blob/master/python/ray/rllib/examples/custom_env.py>`__ and `Carla simulator <https://github.com/ray-project/ray/blob/master/python/ray/rllib/examples/carla/env.py>`__ example env implementations useful as a reference.
 
 Performance
 ~~~~~~~~~~~

doc/source/rllib-models.rst

@@ -46,7 +46,7 @@ Custom models should subclass the common RLlib `model class <https://github.com/
         },
     })
 
-For a full example of a custom model in code, see the `Carla RLlib model <https://github.com/ray-project/ray/blob/master/examples/carla/models.py>`__ and associated `training scripts <https://github.com/ray-project/ray/tree/master/examples/carla>`__. The ``CarlaModel`` class defined there operates over a composite (Tuple) observation space including both images and scalar measurements.
+For a full example of a custom model in code, see the `Carla RLlib model <https://github.com/ray-project/ray/blob/master/python/ray/rllib/examples/carla/models.py>`__ and associated `training scripts <https://github.com/ray-project/ray/tree/master/python/ray/rllib/examples/carla>`__. The ``CarlaModel`` class defined there operates over a composite (Tuple) observation space including both images and scalar measurements.
 
 Custom Preprocessors
 --------------------

examples/carla/README renamed to python/ray/rllib/examples/carla/README

@@ -31,7 +31,6 @@
     "carla-a3c": {
         "run": "A3C",
         "env": "carla_env",
-        "trial_resources": {"cpu": 4, "gpu": 1},
         "config": {
             "env_config": env_config,
             "model": {

examples/carla/a3c_lane_keep.py renamed to python/ray/rllib/examples/carla/a3c_lane_keep.py

@@ -31,7 +31,6 @@
     "carla-dqn": {
         "run": "DQN",
         "env": "carla_env",
-        "trial_resources": {"cpu": 4, "gpu": 1},
         "config": {
             "env_config": env_config,
             "model": {
@@ -49,9 +48,6 @@
             "learning_starts": 1000,
             "schedule_max_timesteps": 100000,
             "gamma": 0.8,
-            "tf_session_args": {
-              "gpu_options": {"allow_growth": True},
-            },
         },
     },
 })

examples/carla/dqn_lane_keep.py renamed to python/ray/rllib/examples/carla/dqn_lane_keep.py

@@ -31,7 +31,6 @@
     "carla-ppo": {
         "run": "PPO",
         "env": "carla_env",
-        "trial_resources": {"cpu": 4, "gpu": 1},
         "config": {
             "env_config": env_config,
             "model": {

examples/carla/env.py renamed to python/ray/rllib/examples/carla/env.py

@@ -32,7 +32,6 @@
     "carla-a3c": {
         "run": "A3C",
         "env": "carla_env",
-        "trial_resources": {"cpu": 5, "extra_gpu": 2},
         "config": {
             "env_config": env_config,
             "use_gpu_for_workers": True,