ray/examples/carla at a5b00a545ea02cb74bd654a0c0520055c75ea1fc - ray

mirror of https://github.com/wassname/ray.git synced 2026-06-28 09:29:05 +08:00

Files

T

Eric Liang 173f1d629a [tune] Ray Tune API cleanup (#1454 )

Remove rllib dep: trainable is now a standalone abstract class that can be easily subclassed.

Clean up hyperband: fix debug string and add an example.

Remove YAML api / ScriptRunner: this was never really used.

Move ray.init() out of run_experiments(): This provides greater flexibility and should be less confusing since there isn't an implicit init() done there. Note that this is a breaking API change for tune.

2018-01-24 16:55:17 -08:00

a3c_lane_keep.py

[tune] Ray Tune API cleanup (#1454 )

2018-01-24 16:55:17 -08:00

dqn_lane_keep.py

[tune] Ray Tune API cleanup (#1454 )

2018-01-24 16:55:17 -08:00

env.py

[carla] [rllib] Add support for carla nav planner and scenarios from paper (#1382 )

2018-01-05 21:32:41 -08:00

models.py

[carla] [rllib] Add support for carla nav planner and scenarios from paper (#1382 )

2018-01-05 21:32:41 -08:00

ppo_lane_keep.py

[tune] Ray Tune API cleanup (#1454 )

2018-01-24 16:55:17 -08:00

README

[carla] [rllib] Add support for carla nav planner and scenarios from paper (#1382 )

2018-01-05 21:32:41 -08:00

scenarios.py

[carla] [rllib] Add support for carla nav planner and scenarios from paper (#1382 )

2018-01-05 21:32:41 -08:00

train_a3c.py

[tune] Ray Tune API cleanup (#1454 )

2018-01-24 16:55:17 -08:00

train_dqn.py

[tune] Ray Tune API cleanup (#1454 )

2018-01-24 16:55:17 -08:00

train_ppo.py

[tune] Ray Tune API cleanup (#1454 )

2018-01-24 16:55:17 -08:00

README

(Experimental) OpenAI gym environment for https://github.com/carla-simulator/carla

To run, first download and unpack the Carla binaries from this URL: https://github.com/carla-simulator/carla/releases/tag/0.7.0

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 CARLA_SERVER=/PATH/TO/CARLA_0.7.0/CarlaUE4.sh
    $ export CARLA_PY_PATH=/PATH/TO/CARLA_BENCHMARK_BRANCH_REPO/PythonClient
    $ python env.py

Check out the scenarios.py file for different training and test scenarios that can be used.