tensorforce.environments package¶
Submodules¶
tensorforce.environments.environment module¶
-
class
tensorforce.environments.environment.
Environment
¶ Bases:
object
Base environment class.
-
__init__
¶ x.init(…) initializes x; see help(type(x)) for signature
-
actions
¶ Return the action space. Might include subdicts if multiple actions are available simultaneously.
Returns: dict of action properties (continuous, number of actions)
-
close
()¶ Close environment. No other method calls possible afterwards.
-
execute
(actions)¶ Executes action, observes next state(s) and reward.
Parameters: actions – Actions to execute. Returns: (Dict of) next state(s), boolean indicating terminal, and reward signal.
-
static
from_spec
(spec, kwargs)¶ Creates an environment from a specification dict.
-
reset
()¶ Reset environment and setup for new episode.
Returns: initial state of reset environment.
-
seed
(seed)¶ Sets the random seed of the environment to the given value (current time, if seed=None). Naturally deterministic Environments (e.g. ALE or some gym Envs) don’t have to implement this method.
Parameters: seed (int) – The seed to use for initializing the pseudo-random number generator (default=epoch time in sec). Returns: The actual seed (int) used OR None if Environment did not override this method (no seeding supported).
-
states
¶ Return the state space. Might include subdicts if multiple states are available simultaneously.
Returns: dict of state properties (shape and type).
-
tensorforce.environments.minimal_test module¶
Module contents¶
-
class
tensorforce.environments.
Environment
¶ Bases:
object
Base environment class.
-
__init__
¶ x.init(…) initializes x; see help(type(x)) for signature
-
actions
¶ Return the action space. Might include subdicts if multiple actions are available simultaneously.
Returns: dict of action properties (continuous, number of actions)
-
close
()¶ Close environment. No other method calls possible afterwards.
-
execute
(actions)¶ Executes action, observes next state(s) and reward.
Parameters: actions – Actions to execute. Returns: (Dict of) next state(s), boolean indicating terminal, and reward signal.
-
static
from_spec
(spec, kwargs)¶ Creates an environment from a specification dict.
-
reset
()¶ Reset environment and setup for new episode.
Returns: initial state of reset environment.
-
seed
(seed)¶ Sets the random seed of the environment to the given value (current time, if seed=None). Naturally deterministic Environments (e.g. ALE or some gym Envs) don’t have to implement this method.
Parameters: seed (int) – The seed to use for initializing the pseudo-random number generator (default=epoch time in sec). Returns: The actual seed (int) used OR None if Environment did not override this method (no seeding supported).
-
states
¶ Return the state space. Might include subdicts if multiple states are available simultaneously.
Returns: dict of state properties (shape and type).
-
-
class
tensorforce.environments.
MinimalTest
(specification)¶ Bases:
tensorforce.environments.environment.Environment
-
__init__
(specification)¶ Initializes a minimal test environment, which is used for the unit tests. Given a specification of actions types and shapes, the environment states consist of the same number of pairs (x, y). The (mean of) an action a gives the next state via (1-a, a), and the ‘correct’ state is always (0, 1).
Parameters: specification – Takes a dict type (keys)-> shape (values specifying the action structure of the environment. Use shape () for single scalar actions.
-
actions
¶
-
close
()¶
-
execute
(actions)¶
-
from_spec
(spec, kwargs)¶ Creates an environment from a specification dict.
-
reset
()¶
-
seed
(seed)¶ Sets the random seed of the environment to the given value (current time, if seed=None). Naturally deterministic Environments (e.g. ALE or some gym Envs) don’t have to implement this method.
Parameters: seed (int) – The seed to use for initializing the pseudo-random number generator (default=epoch time in sec). Returns: The actual seed (int) used OR None if Environment did not override this method (no seeding supported).
-
states
¶
-