Distributions¶
Distributions are customized via the distributions
argument of policy
, for instance:
Agent.create(
...
policy=dict(distributions=dict(
float=dict(type='gaussian', global_stddev=True),
bounded_action=dict(type='beta')
))
...
)
See the policies documentation for more information about how to specify a policy.
-
class
tensorforce.core.distributions.
Categorical
(*, name=None, action_spec=None, input_spec=None)¶ Categorical distribution, for discrete integer actions (specification key:
categorical
).Parameters: - name (string) – internal use.
- action_spec (specification) – internal use.
- input_spec (specification) – internal use.
-
class
tensorforce.core.distributions.
Gaussian
(*, global_stddev=False, bounded_transform='tanh', name=None, action_spec=None, input_spec=None)¶ Gaussian distribution, for continuous actions (specification key:
gaussian
).Parameters: - global_stddev (bool) – Whether to use a separate set of trainable weights to parametrize standard deviation, instead of a state-dependent linear transformation (default: false).
- bounded_transform ("clipping" | "tanh") – Transformation to adjust sampled actions in case of bounded action space (default: tanh).
- name (string) – internal use.
- action_spec (specification) – internal use.
- input_spec (specification) – internal use.
-
class
tensorforce.core.distributions.
Bernoulli
(*, name=None, action_spec=None, input_spec=None)¶ Bernoulli distribution, for binary boolean actions (specification key:
bernoulli
).Parameters: - name (string) – internal use.
- action_spec (specification) – internal use.
- input_spec (specification) – internal use.
-
class
tensorforce.core.distributions.
Beta
(*, name=None, action_spec=None, input_spec=None)¶ Beta distribution, for bounded continuous actions (specification key:
beta
).Parameters: - name (string) – internal use.
- action_spec (specification) – internal use.
- input_spec (specification) – internal use.