POLIXIR REVIVE
1.1.1
What is REVIVE SDK?
Installation
Tutorial
Quick Start
Prepare Data
Define Reward Function
Training Model
Using Model
Task Examples
Example of applying REVIVE to gym-pendulum
Example of applying REVIVE to Lander Hover
Use REVIVE to control your refrigerator
Use REVIVE to control industrial machines
Controlling Mujoco-HalfCheetah using REVIVE SDK
Controlling Mujoco-HalfCheetah using Revive_filter
Advanced Tools
Add External Factor
Add Expert Functions
Multi-Time-Steps Data Nodes
Append Time Step Index as Node Input
Freeze network parameters of some nodes
Heterogeneous Decision Flow Loading
Introduction to Empty Nodes
Loss function of user-defined node
Generate Decision Flow through Causal Inference
Customize Network Decision Nodes
Introducing expert rule constraints
Training Control Policies with Multiple Nodes
Introduction to Multi-Discriminator
Neural Network Disturber
Training Results
Virtual Environment Training Results
Policy Training Results
Response Curve
Model Dynamic Interaction Features
Data Feature Relationship Analysis and Visualization [Beta]
Revive API
revive.server
revive.computation
revive.conf
Other
FAQ
Releases
POLIXIR REVIVE
revive.common package
View page source
revive.common package
¶
Submodules
¶
revive.common.next_ts_policy_function module
¶
revive.common.next_ts_policy_function.
next_ts_placeholder_policy_function
(
data
:
Dict
[
str
,
Tensor
]
)
→
Tensor
[source]
¶
revive.common.next_ts_transition_function module
¶
revive.common.next_ts_transition_function.
next_ts_placeholder_transition_function
(
data
:
Dict
[
str
,
Tensor
]
)
→
Tensor
[source]
¶
revive.common.step_node_function module
¶
revive.common.step_node_function.
get_next_step_node
(
data
:
Dict
[
str
,
Tensor
]
)
→
Tensor
[source]
¶
Module contents
¶