Benchmarking

All benchmark results are available in the benchmark_results.md. If you wish to run all benchmarks locally, feel free to run them with:

$ python src/bencmark/benchmark.py

This command will run all implemented methods with all available datasets. Be careful, it will take a long time! If you wish to run a single method or run them in parallel, use:

$ python src/bencmark/benchmark.py --methods <METHOD NAME>

For example:

$ python src/bencmark/benchmark.py --methods bc,bco

will run Behavioural Cloning and Behavioural Clonning from Observation.