BARK-ML - Machine Learning for Autonomous Driving

BARK-ML provides simple-to-use OpenAi-Gym environments for several scenarios, such as highway driving, merging and intersections. Additionally, BARK-ML integrates state-of-the-art machine learning libraries to learn driving behaviors for autonomous vehicles.

BARK-ML supported machine learning libraries:

• TF-Agents
• Baselines (Planned)
• Diadem
• tf2rl

Gym Environments

Before running the examples, install the virtual python environment (bash utils/install.sh) and enter it (source utils/dev_into.sh).

Continuous environments: bazel run //examples:continuous_env

Available environments:

• highway-v0: Continuous highway environment
• highway-v1: Discrete highway environment
• merging-v0: Continuous merging environment
• merging-v1: Discrete merging environment
• intersection-v0: Continuous intersection environment
• intersection-v1: Discrete intersection environment

TF-Agents

TF-Agents SAC-example: bazel run //examples:tfa.

GAIL

Running tests

# Separate sets of tests

bazel test :unit_tests  
bazel test :examples_tests
bazel test :gail_tests
bazel test :generate_load_tests

# All test sets combined
bazel test :all_tests

# All tests in workspace
bazel test //...

License

BARK-ML specific code is distributed under MIT License.