[carla] [rllib] Add support for carla nav planner and scenarios from …

…paper (#1382) * wip * Sat Dec 30 15:07:28 PST 2017 * log video * video doesn't work well * scenario integration * Sat Dec 30 17:30:22 PST 2017 * Sat Dec 30 17:31:05 PST 2017 * Sat Dec 30 17:31:32 PST 2017 * Sat Dec 30 17:32:16 PST 2017 * Sat Dec 30 17:34:11 PST 2017 * Sat Dec 30 17:34:50 PST 2017 * Sat Dec 30 17:35:34 PST 2017 * Sat Dec 30 17:38:49 PST 2017 * Sat Dec 30 17:40:39 PST 2017 * Sat Dec 30 17:43:00 PST 2017 * Sat Dec 30 17:43:04 PST 2017 * Sat Dec 30 17:45:56 PST 2017 * Sat Dec 30 17:46:26 PST 2017 * Sat Dec 30 17:47:02 PST 2017 * Sat Dec 30 17:51:53 PST 2017 * Sat Dec 30 17:52:54 PST 2017 * Sat Dec 30 17:56:43 PST 2017 * Sat Dec 30 18:27:07 PST 2017 * Sat Dec 30 18:27:52 PST 2017 * fix train * Sat Dec 30 18:41:51 PST 2017 * Sat Dec 30 18:54:11 PST 2017 * Sat Dec 30 18:56:22 PST 2017 * Sat Dec 30 19:05:04 PST 2017 * Sat Dec 30 19:05:23 PST 2017 * Sat Dec 30 19:11:53 PST 2017 * Sat Dec 30 19:14:31 PST 2017 * Sat Dec 30 19:16:20 PST 2017 * Sat Dec 30 19:18:05 PST 2017 * Sat Dec 30 19:18:45 PST 2017 * Sat Dec 30 19:22:44 PST 2017 * Sat Dec 30 19:24:41 PST 2017 * Sat Dec 30 19:26:57 PST 2017 * Sat Dec 30 19:40:37 PST 2017 * wip models * reward bonus * test prep * Sun Dec 31 18:45:25 PST 2017 * Sun Dec 31 18:58:28 PST 2017 * Sun Dec 31 18:59:34 PST 2017 * Sun Dec 31 19:03:33 PST 2017 * Sun Dec 31 19:05:05 PST 2017 * Sun Dec 31 19:09:25 PST 2017 * fix train * kill * add tuple preprocessor * Sun Dec 31 20:38:33 PST 2017 * Sun Dec 31 22:51:24 PST 2017 * Sun Dec 31 23:14:13 PST 2017 * Sun Dec 31 23:16:04 PST 2017 * Mon Jan 1 00:08:35 PST 2018 * Mon Jan 1 00:10:48 PST 2018 * Mon Jan 1 01:08:31 PST 2018 * Mon Jan 1 14:45:44 PST 2018 * Mon Jan 1 14:54:56 PST 2018 * Mon Jan 1 17:29:29 PST 2018 * switch to euclidean dists * Mon Jan 1 17:39:27 PST 2018 * Mon Jan 1 17:41:47 PST 2018 * Mon Jan 1 17:44:18 PST 2018 * Mon Jan 1 17:47:09 PST 2018 * Mon Jan 1 20:31:02 PST 2018 * Mon Jan 1 20:39:33 PST 2018 * Mon Jan 1 20:40:55 PST 2018 * Mon Jan 1 20:55:06 PST 2018 * Mon Jan 1 21:05:52 PST 2018 * fix env path * merge richards fix * fix hash * Mon Jan 1 22:04:00 PST 2018 * Mon Jan 1 22:25:29 PST 2018 * Mon Jan 1 22:30:42 PST 2018 * simplified reward function * add framestack * add env configs * simplify speed reward * Tue Jan 2 17:36:15 PST 2018 * Tue Jan 2 17:49:16 PST 2018 * Tue Jan 2 18:10:38 PST 2018 * add lane keeping simple mode * Tue Jan 2 20:25:26 PST 2018 * Tue Jan 2 20:30:30 PST 2018 * Tue Jan 2 20:33:26 PST 2018 * Tue Jan 2 20:41:42 PST 2018 * ppo lane keep * simplify discrete actions * Tue Jan 2 21:41:05 PST 2018 * Tue Jan 2 21:49:03 PST 2018 * Tue Jan 2 22:12:23 PST 2018 * Tue Jan 2 22:14:42 PST 2018 * Tue Jan 2 22:20:59 PST 2018 * Tue Jan 2 22:23:43 PST 2018 * Tue Jan 2 22:26:27 PST 2018 * Tue Jan 2 22:27:20 PST 2018 * Tue Jan 2 22:44:00 PST 2018 * Tue Jan 2 22:57:58 PST 2018 * Tue Jan 2 23:08:51 PST 2018 * Tue Jan 2 23:11:32 PST 2018 * update dqn reward * Thu Jan 4 12:29:40 PST 2018 * Thu Jan 4 12:30:26 PST 2018 * Update train_dqn.py * fix
ray-project · Jan 6, 2018 · c60ccba · c60ccba
1 parent 088f014
commit c60ccba
Show file tree

Hide file tree

Showing 25 changed files with 1,013 additions and 218 deletions.
diff --git a/doc/source/rllib.rst b/doc/source/rllib.rst
@@ -157,7 +157,7 @@ can register a function that creates the env to refer to it by name. For example
     from ray.tune.registry import register_env
     from ray.rllib import ppo
 
-    env_creator = lambda: create_my_env()
+    env_creator = lambda env_config: create_my_env()
     env_creator_name = "custom_env"
     register_env(env_creator_name, env_creator)
 

diff --git a/examples/carla/README b/examples/carla/README
@@ -1,12 +1,14 @@
-(Experimental) gym environment for https://github.com/carla-simulator/carla
+(Experimental) OpenAI gym environment for https://github.com/carla-simulator/carla
 
-To run, first download and unpack the Carla release from this URL: https://github.com/carla-simulator/carla/releases/tag/0.7.0
+To run, first download and unpack the Carla binaries from this URL: https://github.com/carla-simulator/carla/releases/tag/0.7.0
 
-Then, you can try running env.py to drive the car. Run train_ppo.py or train_dqn.py to attempt training.
+Note that currently you also need to clone the Python code from `carla/benchmark_branch` which includes the Carla planner.
+
+Then, you can try running env.py to drive the car. Run one of the train_* scripts to attempt training.
 
     $ pkill -9 Carla
-    $ export PYTHONPATH=/home/ubuntu/CARLA_0.7.0/PythonClient:$PYTHONPATH
-    $ export CARLA_SERVER=/home/ubuntu/CARLA_0.7.0/CarlaUE4.sh
+    $ export CARLA_SERVER=/PATH/TO/CARLA_0.7.0/CarlaUE4.sh
+    $ export CARLA_PY_PATH=/PATH/TO/CARLA_BENCHMARK_BRANCH_REPO/PythonClient
     $ python env.py
 
-Note that the reward function is currently hard-coded to drive straight down the street.
+Check out the scenarios.py file for different training and test scenarios that can be used.
diff --git a/examples/carla/a3c_lane_keep.py b/examples/carla/a3c_lane_keep.py
@@ -0,0 +1,50 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from ray.tune import register_env, run_experiments
+
+from env import CarlaEnv, ENV_CONFIG
+from models import register_carla_model
+from scenarios import LANE_KEEP
+
+env_name = "carla_env"
+env_config = ENV_CONFIG.copy()
+env_config.update({
+    "verbose": False,
+    "x_res": 80,
+    "y_res": 80,
+    "use_depth_camera": False,
+    "discrete_actions": False,
+    "server_map": "/Game/Maps/Town02",
+    "reward_function": "lane_keep",
+    "enable_planner": False,
+    "scenarios": [LANE_KEEP],
+})
+
+register_env(env_name, lambda env_config: CarlaEnv(env_config))
+register_carla_model()
+
+run_experiments({
+    "carla-a3c": {
+        "run": "A3C",
+        "env": "carla_env",
+        "resources": {"cpu": 4, "gpu": 1},
+        "config": {
+            "env_config": env_config,
+            "model": {
+                "custom_model": "carla",
+                "custom_options": {
+                    "image_shape": [80, 80, 6],
+                },
+                "conv_filters": [
+                    [16, [8, 8], 4],
+                    [32, [4, 4], 2],
+                    [512, [10, 10], 1],
+                ],
+            },
+            "gamma": 0.8,
+            "num_workers": 1,
+        },
+    },
+})
diff --git a/examples/carla/dqn_lane_keep.py b/examples/carla/dqn_lane_keep.py
@@ -0,0 +1,55 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from ray.tune import register_env, run_experiments
+
+from env import CarlaEnv, ENV_CONFIG
+from models import register_carla_model
+from scenarios import LANE_KEEP
+
+env_name = "carla_env"
+env_config = ENV_CONFIG.copy()
+env_config.update({
+    "verbose": False,
+    "x_res": 80,
+    "y_res": 80,
+    "use_depth_camera": False,
+    "discrete_actions": True,
+    "server_map": "/Game/Maps/Town02",
+    "reward_function": "lane_keep",
+    "enable_planner": False,
+    "scenarios": [LANE_KEEP],
+})
+
+register_env(env_name, lambda env_config: CarlaEnv(env_config))
+register_carla_model()
+
+run_experiments({
+    "carla-dqn": {
+        "run": "DQN",
+        "env": "carla_env",
+        "resources": {"cpu": 4, "gpu": 1},
+        "config": {
+            "env_config": env_config,
+            "model": {
+                "custom_model": "carla",
+                "custom_options": {
+                    "image_shape": [80, 80, 6],
+                },
+                "conv_filters": [
+                    [16, [8, 8], 4],
+                    [32, [4, 4], 2],
+                    [512, [10, 10], 1],
+                ],
+            },
+            "timesteps_per_iteration": 100,
+            "learning_starts": 1000,
+            "schedule_max_timesteps": 100000,
+            "gamma": 0.8,
+            "tf_session_args": {
+              "gpu_options": {"allow_growth": True},
+            },
+        },
+    },
+})