def test_cartpole(alg): ''' Test if the algorithm (with an mlp policy) can learn to balance the cartpole ''' kwargs = common_kwargs.copy() kwargs.update(learn_kwargs[alg]) learn_fn = lambda e: get_learn_function(alg)(env=e, **kwargs) def env_fn(): env = gym.make('CartPole-v0') env.seed(0) return env reward_per_episode_test(env_fn, learn_fn, 100)
def test_fetchreach(alg): ''' Test if the algorithm (with an mlp policy) can learn the FetchReach task ''' kwargs = common_kwargs.copy() kwargs.update(learn_kwargs[alg]) learn_fn = lambda e: get_learn_function(alg)(env=e, **kwargs) def env_fn(): env = gym.make('FetchReach-v1') env.seed(0) return env reward_per_episode_test(env_fn, learn_fn, -15)