Save model to a pickle located at `path`

Creates the act function: Parameters ---------- make_obs_ph: str -> tf.placeholder or TfInput a function that take a name and creates a p

Creates the act function with support for parameter space noise exploration (https://arxiv.org/abs/1706.01905): Parameters ---------- make_obs_

This model takes as input an observation and returns values of all actions. Parameters ---------- convs: [(int, int int)] list of convolu

Train a acktr model. Parameters ------- env_id: environment to train on num_timesteps: int number of env steps to optimizer f

Train a dqn model. Parameters ------- env_id: environment to train on num_timesteps: int number of env steps to optimizer for

Creates the train function: Parameters ---------- make_obs_ph: str -> tf.placeholder or TfInput a function that takes a name and creates

Train a deepq model. Parameters ------- env: gym.Env environment to train on q_func: (tf.Variable, int, str, bool) -> tf.Variable

Load act function that was returned by learn function. Parameters ---------- path: str path to the act function pickle num_cpu: int

This model takes as input an observation and returns values of all actions. Parameters ---------- hiddens: [int] list of sizes of hidden