diff --git a/baselines/ddpg/test_smoke.py b/baselines/ddpg/test_smoke.py new file mode 100644 index 0000000..b5bf866 --- /dev/null +++ b/baselines/ddpg/test_smoke.py @@ -0,0 +1,17 @@ +from baselines.run import main as M + +def _run(argstr): + M(('--alg=ddpg --env=Pendulum-v0 --num_timesteps=0 ' + argstr).split(' ')) + +def test_popart(): + _run('--normalize_returns=True --popart=True') + +def test_noise_normal(): + _run('--noise_type=normal_0.1') + +def test_noise_ou(): + _run('--noise_type=ou_0.1') + +def test_noise_adaptive(): + _run('--noise_type=adaptive-param_0.2,normal_0.1') + diff --git a/baselines/run.py b/baselines/run.py index c0298f3..609de6e 100644 --- a/baselines/run.py +++ b/baselines/run.py @@ -181,11 +181,11 @@ def parse_cmdline_kwargs(args): -def main(): +def main(args): # configure logger, disable logging in child MPI processes (with rank > 0) arg_parser = common_arg_parser() - args, unknown_args = arg_parser.parse_known_args() + args, unknown_args = arg_parser.parse_known_args(args) extra_args = parse_cmdline_kwargs(unknown_args) if MPI is None or MPI.COMM_WORLD.Get_rank() == 0: @@ -220,5 +220,7 @@ def main(): env.close() + return model + if __name__ == '__main__': - main() + main(sys.argv)