gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 11:10:20 +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

27
rl_coach/agents/ddpg_agent.py
View File

@@ -65,6 +65,33 @@ class DDPGActorNetworkParameters(NetworkParameters):
class DDPGAlgorithmParameters(AlgorithmParameters):
"""
:param num_steps_between_copying_online_weights_to_target: (StepMethod)
The number of steps between copying the online network weights to the target network weights.
:param rate_for_copying_weights_to_target: (float)
When copying the online network weights to the target network weights, a soft update will be used, which
weight the new online network weights by rate_for_copying_weights_to_target
:param num_consecutive_playing_steps: (StepMethod)
The number of consecutive steps to act between every two training iterations
:param use_target_network_for_evaluation: (bool)
If set to True, the target network will be used for predicting the actions when choosing actions to act.
Since the target network weights change more slowly, the predicted actions will be more consistent.
:param action_penalty: (float)
The amount by which to penalize the network on high action feature (pre-activation) values.
This can prevent the actions features from saturating the TanH activation function, and therefore prevent the
gradients from becoming very low.
:param clip_critic_targets: (Tuple[float, float] or None)
The range to clip the critic target to in order to prevent overestimation of the action values.
:param use_non_zero_discount_for_terminal_states: (bool)
If set to True, the discount factor will be used for terminal states to bootstrap the next predicted state
values. If set to False, the terminal states reward will be taken as the target return for the network.
"""
def __init__(self):
super().__init__()
self.num_steps_between_copying_online_weights_to_target = EnvironmentSteps(1)