gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 11:40:18 +01:00
Code Issues Projects Releases Wiki Activity

update of api docstrings across coach and tutorials [WIP] (#91)

Browse Source 
* updating the documentation website
* adding the built docs
* update of api docstrings across coach and tutorials 0-2
* added some missing api documentation
* New Sphinx based documentation
This commit is contained in:
Itai Caspi
2018-11-15 15:00:13 +02:00
committed by Gal Novik
parent 524f8436a2
commit 6d40ad1650
517 changed files with 71034 additions and 12834 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
rl_coach/agents/actor_critic_agent.py
View File

@@ -36,25 +36,25 @@ from rl_coach.utils import last_sample
class ActorCriticAlgorithmParameters(AlgorithmParameters):
"""
:param policy_gradient_rescaler: (PolicyGradientRescaler)
The value that will be used to rescale the policy gradient
The value that will be used to rescale the policy gradient
:param apply_gradients_every_x_episodes: (int)
The number of episodes to wait before applying the accumulated gradients to the network.
The training iterations only accumulate gradients without actually applying them.
The number of episodes to wait before applying the accumulated gradients to the network.
The training iterations only accumulate gradients without actually applying them.
:param beta_entropy: (float)
The weight that will be given to the entropy regularization which is used in order to improve exploration.
The weight that will be given to the entropy regularization which is used in order to improve exploration.
:param num_steps_between_gradient_updates: (int)
Every num_steps_between_gradient_updates transitions will be considered as a single batch and use for
accumulating gradients. This is also the number of steps used for bootstrapping according to the n-step formulation.
Every num_steps_between_gradient_updates transitions will be considered as a single batch and use for
accumulating gradients. This is also the number of steps used for bootstrapping according to the n-step formulation.
:param gae_lambda: (float)
If the policy gradient rescaler was defined as PolicyGradientRescaler.GAE, the generalized advantage estimation
scheme will be used, in which case the lambda value controls the decay for the different n-step lengths.
If the policy gradient rescaler was defined as PolicyGradientRescaler.GAE, the generalized advantage estimation
scheme will be used, in which case the lambda value controls the decay for the different n-step lengths.
:param estimate_state_value_using_gae: (bool)
If set to True, the state value targets for the V head will be estimated using the GAE scheme.
If set to True, the state value targets for the V head will be estimated using the GAE scheme.
"""
def __init__(self):
super().__init__()