py env atari argparse Argparse TensorFlow feedforward envs VecEnv pretrain petrained tf th nn np str mujoco cpu ndarray ndarrays timestep timesteps stepsize dataset adam fn normalisation Kullback Leibler boolean deserialized pretrained minibatch subprocesses ArgumentParser Tensorflow Gaussian approximator minibatches hyperparameters hyperparameter vectorized rl colab dataloader npz datasets vf logits num Utils backpropagate prepend NaN preprocessing Cloudpickle async multiprocess tensorflow mlp cnn neglogp tanh coef repo Huber params ppo arxiv Arxiv func DQN Uhlenbeck Ornstein multithread cancelled Tensorboard parallelize customising serializable Multiprocessed cartpole toolset lstm rescale ffmpeg avconv unnormalized Github pre preprocess backend attr preprocess Antonin Raffin araffin Homebrew Numpy Theano rollout kfac Piecewise csv nvidia visdom tensorboard preprocessed namespace sklearn GoalEnv Torchy pytorch dicts optimizers Deprecations forkserver cuda Polyak gSDE rollouts quantiles quantile contrib Contrib