tensorforce package¶
Subpackages¶
- tensorforce.agents package
- Submodules
- tensorforce.agents.agent module
- tensorforce.agents.batch_agent module
- tensorforce.agents.constant_agent module
- tensorforce.agents.ddqn_agent module
- tensorforce.agents.dqfd_agent module
- tensorforce.agents.dqn_agent module
- tensorforce.agents.dqn_nstep_agent module
- tensorforce.agents.memory_agent module
- tensorforce.agents.naf_agent module
- tensorforce.agents.ppo_agent module
- tensorforce.agents.random_agent module
- tensorforce.agents.trpo_agent module
- tensorforce.agents.vpg_agent module
- Module contents
- tensorforce.contrib package
- Submodules
- tensorforce.contrib.ale module
- tensorforce.contrib.deepmind_lab module
- tensorforce.contrib.maze_explorer module
- tensorforce.contrib.openai_gym module
- tensorforce.contrib.openai_universe module
- tensorforce.contrib.remote_environment module
- tensorforce.contrib.state_settable_environment module
- tensorforce.contrib.unreal_engine module
- Module contents
- tensorforce.core package
- Subpackages
- tensorforce.core.baselines package
- tensorforce.core.distributions package
- tensorforce.core.explorations package
- Submodules
- tensorforce.core.explorations.constant module
- tensorforce.core.explorations.epsilon_anneal module
- tensorforce.core.explorations.epsilon_decay module
- tensorforce.core.explorations.exploration module
- tensorforce.core.explorations.linear_decay module
- tensorforce.core.explorations.ornstein_uhlenbeck_process module
- Module contents
- tensorforce.core.memories package
- tensorforce.core.networks package
- tensorforce.core.optimizers package
- Subpackages
- Submodules
- tensorforce.core.optimizers.clipped_step module
- tensorforce.core.optimizers.evolutionary module
- tensorforce.core.optimizers.global_optimizer module
- tensorforce.core.optimizers.meta_optimizer module
- tensorforce.core.optimizers.multi_step module
- tensorforce.core.optimizers.natural_gradient module
- tensorforce.core.optimizers.optimized_step module
- tensorforce.core.optimizers.optimizer module
- tensorforce.core.optimizers.synchronization module
- tensorforce.core.optimizers.tf_optimizer module
- Module contents
- tensorforce.core.preprocessing package
- Submodules
- tensorforce.core.preprocessing.clip module
- tensorforce.core.preprocessing.divide module
- tensorforce.core.preprocessing.grayscale module
- tensorforce.core.preprocessing.image_resize module
- tensorforce.core.preprocessing.normalize module
- tensorforce.core.preprocessing.preprocessor module
- tensorforce.core.preprocessing.preprocessor_stack module
- tensorforce.core.preprocessing.running_standardize module
- tensorforce.core.preprocessing.sequence module
- tensorforce.core.preprocessing.standardize module
- Module contents
- Module contents
- Subpackages
- tensorforce.environments package
- tensorforce.execution package
- tensorforce.models package
- Submodules
- tensorforce.models.constant_model module
- tensorforce.models.distribution_model module
- tensorforce.models.model module
- tensorforce.models.pg_log_prob_model module
- tensorforce.models.pg_model module
- tensorforce.models.pg_prob_ratio_model module
- tensorforce.models.q_demo_model module
- tensorforce.models.q_model module
- tensorforce.models.q_naf_model module
- tensorforce.models.q_nstep_model module
- tensorforce.models.random_model module
- Module contents
- tensorforce.tests package
- Submodules
- tensorforce.tests.base_agent_test module
- tensorforce.tests.base_test module
- tensorforce.tests.test_constant_agent module
- tensorforce.tests.test_ddqn_agent module
- tensorforce.tests.test_dqfd_agent module
- tensorforce.tests.test_dqn_agent module
- tensorforce.tests.test_dqn_memories module
- tensorforce.tests.test_dqn_nstep_agent module
- tensorforce.tests.test_naf_agent module
- tensorforce.tests.test_ppo_agent module
- tensorforce.tests.test_quickstart_example module
- tensorforce.tests.test_random_agent module
- tensorforce.tests.test_reward_estimation module
- tensorforce.tests.test_trpo_agent module
- tensorforce.tests.test_tutorial_code module
- tensorforce.tests.test_vpg_agent module
- tensorforce.tests.test_vpg_baselines module
- tensorforce.tests.test_vpg_optimizers module
- Module contents
Submodules¶
tensorforce.exception module¶
-
exception
tensorforce.exception.
TensorForceError
¶ Bases:
exceptions.Exception
TensorForce error
tensorforce.meta_parameter_recorder module¶
-
class
tensorforce.meta_parameter_recorder.
MetaParameterRecorder
(current_frame)¶ Bases:
object
Class to record MetaParameters as well as Summary/Description for TensorBoard (TEXT & FILE will come later)
General:
- format_type: used to configure data conversion for TensorBoard=0, TEXT & JSON (not Implemented), etc
-
build_metagraph_list
()¶ Convert MetaParams into TF Summary Format and create summary_op
Parameters: None – Returns: Merged TF Op for TEXT summary elements, should only be executed once to reduce data duplication
-
convert_data_to_string
(data, indent=0, format_type=0, separator=None, eol=None)¶
-
convert_dictionary_to_string
(data, indent=0, format_type=0, separator=None, eol=None)¶
-
convert_list_to_string
(data, indent=0, format_type=0, eol=None, count=True)¶
-
convert_ndarray_to_md
(data, format_type=0, eol=None)¶
-
merge_custom
(custom_dict)¶
-
text_output
(format_type=1)¶
tensorforce.util module¶
-
tensorforce.util.
cumulative_discount
(values, terminals, discount, cumulative_start=0.0)¶ Compute cumulative discounts. :param values: Values to discount :param terminals: Booleans indicating terminal states :param discount: Discount factor :param cumulative_start: Float or ndarray, estimated reward for state t + 1. Default 0.0
Returns: The cumulative discounted rewards. Return type: dicounted_values
-
tensorforce.util.
get_object
(obj, predefined_objects=None, default_object=None, kwargs=None)¶ Utility method to map some kind of object specification to its content, e.g. optimizer or baseline specifications to the respective classes.
Parameters: - obj – A specification dict (value for key ‘type’ optionally specifies the object, options as follows), a module path (e.g., my_module.MyClass), a key in predefined_objects, or a callable (e.g., the class type object).
- predefined_objects – Dict containing predefined set of objects, accessible via their key
- default_object – Default object is no other is specified
- kwargs – Arguments for object creation
Returns: The retrieved object
-
tensorforce.util.
np_dtype
(dtype)¶ Translates dtype specifications in configurations to numpy data types. :param dtype: String describing a numerical type (e.g. ‘float’) or numerical type primitive.
Returns: Numpy data type
-
tensorforce.util.
prod
(xs)¶ Computes the product along the elements in an iterable. Returns 1 for empty iterable.
Parameters: xs – Iterable containing numbers. Returns: Product along iterable.
-
tensorforce.util.
rank
(x)¶
-
tensorforce.util.
shape
(x, unknown=-1)¶
-
tensorforce.util.
tf_dtype
(dtype)¶ Translates dtype specifications in configurations to tensorflow data types.
Parameters: dtype – String describing a numerical type (e.g. ‘float’), numpy data type, or numerical type primitive. Returns: TensorFlow data type