garage.tf package

Tensorflow Branch.

paths_to_tensors(paths, max_path_length, baseline_predictions, discount, gae_lambda)

Return processed sample data based on the collected paths.

Parameters:

• paths (list[dict]) – A list of collected paths.
• max_path_length (int) – Maximum length of a single rollout.
• baseline_predictions (numpy.ndarray) – : Predicted value of GAE (Generalized Advantage Estimation) Baseline.
• discount (float) – Environment reward discount.
• gae_lambda (float) – Lambda used for generalized advantage estimation.

Returns:

Processed sample data, with key

• observations: (numpy.ndarray)
• actions: (numpy.ndarray)
• rewards: (numpy.ndarray)
• baselines: (numpy.ndarray)
• returns: (numpy.ndarray)
• valids: (numpy.ndarray)
• agent_infos: (dict)
• env_infos: (dict)
• paths: (list[dict])

Return type:

dict

Subpackages

• garage.tf.algos package
  • Submodules
    • garage.tf.algos.ddpg module
    • garage.tf.algos.dqn module
    • garage.tf.algos.erwr module
    • garage.tf.algos.npo module
    • garage.tf.algos.ppo module
    • garage.tf.algos.reps module
    • garage.tf.algos.rl2 module
    • garage.tf.algos.rl2ppo module
    • garage.tf.algos.rl2trpo module
    • garage.tf.algos.td3 module
    • garage.tf.algos.te module
    • garage.tf.algos.te_npo module
    • garage.tf.algos.te_ppo module
    • garage.tf.algos.tnpg module
    • garage.tf.algos.trpo module
    • garage.tf.algos.vpg module
• garage.tf.baselines package
  • Submodules
    • garage.tf.baselines.continuous_mlp_baseline module
    • garage.tf.baselines.gaussian_cnn_baseline module
    • garage.tf.baselines.gaussian_mlp_baseline module
• garage.tf.distributions package
  • Submodules
    • garage.tf.distributions.bernoulli module
    • garage.tf.distributions.categorical module
    • garage.tf.distributions.diagonal_gaussian module
    • garage.tf.distributions.distribution module
    • garage.tf.distributions.recurrent_categorical module
    • garage.tf.distributions.recurrent_diagonal_gaussian module
• garage.tf.embeddings package
  • Submodules
    • garage.tf.embeddings.encoder module
    • garage.tf.embeddings.gaussian_mlp_encoder module
• garage.tf.misc package
  • Submodules
    • garage.tf.misc.tensor_utils module
• garage.tf.models package
  • Submodules
    • garage.tf.models.categorical_cnn_model module
    • garage.tf.models.categorical_gru_model module
    • garage.tf.models.categorical_lstm_model module
    • garage.tf.models.categorical_mlp_model module
    • garage.tf.models.cnn module
    • garage.tf.models.cnn_mlp_merge_model module
    • garage.tf.models.cnn_model module
    • garage.tf.models.cnn_model_max_pooling module
    • garage.tf.models.gaussian_cnn_model module
    • garage.tf.models.gaussian_gru_model module
    • garage.tf.models.gaussian_lstm_model module
    • garage.tf.models.gaussian_mlp_model module
    • garage.tf.models.gru module
    • garage.tf.models.gru_model module
    • garage.tf.models.lstm module
    • garage.tf.models.lstm_model module
    • garage.tf.models.mlp module
    • garage.tf.models.mlp_dueling_model module
    • garage.tf.models.mlp_merge_model module
    • garage.tf.models.mlp_model module
    • garage.tf.models.model module
    • garage.tf.models.module module
    • garage.tf.models.normalized_input_mlp_model module
    • garage.tf.models.parameter module
    • garage.tf.models.sequential module
• garage.tf.optimizers package
  • Submodules
    • garage.tf.optimizers.conjugate_gradient_optimizer module
    • garage.tf.optimizers.first_order_optimizer module
    • garage.tf.optimizers.lbfgs_optimizer module
    • garage.tf.optimizers.penalty_lbfgs_optimizer module
    • garage.tf.optimizers.utils module
• garage.tf.plotter package
  • Submodules
    • garage.tf.plotter.plotter module
• garage.tf.policies package
  • Submodules
    • garage.tf.policies.categorical_cnn_policy module
    • garage.tf.policies.categorical_gru_policy module
    • garage.tf.policies.categorical_lstm_policy module
    • garage.tf.policies.categorical_mlp_policy module
    • garage.tf.policies.continuous_mlp_policy module
    • garage.tf.policies.discrete_qf_derived_policy module
    • garage.tf.policies.gaussian_gru_policy module
    • garage.tf.policies.gaussian_lstm_policy module
    • garage.tf.policies.gaussian_mlp_policy module
    • garage.tf.policies.gaussian_mlp_task_embedding_policy module
    • garage.tf.policies.policy module
    • garage.tf.policies.task_embedding_policy module
    • garage.tf.policies.uniform_control_policy module
• garage.tf.q_functions package
  • Submodules
    • garage.tf.q_functions.continuous_cnn_q_function module
    • garage.tf.q_functions.continuous_mlp_q_function module
    • garage.tf.q_functions.discrete_cnn_q_function module
    • garage.tf.q_functions.discrete_mlp_q_function module
    • garage.tf.q_functions.q_function module
• garage.tf.regressors package
  • Submodules
    • garage.tf.regressors.bernoulli_mlp_regressor module
    • garage.tf.regressors.categorical_mlp_regressor module
    • garage.tf.regressors.categorical_mlp_regressor_model module
    • garage.tf.regressors.continuous_mlp_regressor module
    • garage.tf.regressors.gaussian_cnn_regressor module
    • garage.tf.regressors.gaussian_cnn_regressor_model module
    • garage.tf.regressors.gaussian_mlp_regressor module
    • garage.tf.regressors.gaussian_mlp_regressor_model module
    • garage.tf.regressors.regressor module
• garage.tf.samplers package
  • Submodules
    • garage.tf.samplers.batch_sampler module
    • garage.tf.samplers.worker module