Determining causal models for controlling environments

Patent metadata

Field	Value
Publication number	US-12282304-B2
Application number	US-202318210700-A
Country	US
Kind code	B2
Filing date	Jun 16, 2023
Priority date	Mar 15, 2019
Publication date	Apr 22, 2025
Grant date	Apr 22, 2025

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes obtaining data specifying baseline probability distributions for each of a plurality of controllable elements; maintaining a causal model; repeatedly performing the following: selecting control settings for the environment based on the causal model and values for a particular internal parameter of the control system that are sampled from a range of possible values; selecting control settings for the environment based on the baseline probability distributions; monitoring environment responses to the control settings selected based on the causal model and the control settings selected based on the baseline probability distributions; determining, for each of the possible values, a measure of a difference between a current system performance and a baseline system performance; and updating how frequently each of the possible values is sampled.

First claim

What is claimed is:

1. A method comprising:
obtaining data specifying baseline probability distributions over possible settings for each of a plurality of controllable elements;
maintaining a causal model that identifies causal relationships between the possible settings and responses to the possible settings;
repeatedly performing the following:
selecting, control settings based on the causal model and values for a parameter of a system that are sampled from a range of possible values for the parameter;
selecting control settings based on the baseline probability distributions;
monitoring responses to (i) the control settings selected based on the causal model and (ii) the control settings selected based on the baseline probability distributions;
determining, for each of the possible values of the parameter, a difference between (i) a system performance when the control settings are selected based on the causal model and on the possible value of the parameter and (ii) a system performance measure for the control settings selected based on the baseline probability distributions; and
updating how frequently each of the possible values is sampled based on the measures of difference.

2. The method of claim 1 , wherein the parameter is a data inclusion window that defines how many previously received environment responses are used to update the causal model.

3. The method of claim 1 , wherein the parameter is a temporal extent parameter that defines which environment responses are associated with which selection of control settings in the causal model.

4. The method of claim 1 , wherein the parameter is a ratio parameter that defines how frequently control settings are selected using the baseline probability distributions relative to being selected using the causal model.

5. The method of claim 1 , wherein the parameter is a clustering parameter that is a hyperparameter of a clustering technique employed to cluster procedural instances in the environment into clusters when selecting control settings for the procedural instances.

6. The method of claim 5 , further comprising:
adjusting the range of possible values for the parameter during operation of the system.

7. The method of claim 6 , further comprising:
adjusting the range of possible values based on a statistical power analysis of a statistical power of the second causal model.

8. The method of claim 1 , the method further comprising:
maintaining a second causal model that identifies causal relationships between the possible values for the parameter and the measure of the difference, wherein:
the possible values are sampled based on the second causal model, and
updating how frequently each of the possible values comprises updating the second causal model based on the measures of difference.

9. The method of claim 8 , wherein the second causal model comprises, for each possible value for the particular internal parameter, (i) an impact measurement that measures the impact of the possible value on the measure of difference and (ii) a confidence interval that represents a level of uncertainty about the impact measurement.

10. The method of claim 8 , wherein the possible values are sampled by mapping the impact measurements and the confidence intervals to a probability distribution over the possible values and sampling a value from the probability distribution.

11. The method of claim 1 , further comprising setting a value of a ratio parameter by performing a statistical power analysis to compute a minimum number of baseline instances that are required to determine that hybrid instances outperform the baseline instances with a threshold statistic power.

12. The method of claim 11 , further comprising adjusting a value of the ratio parameter to be
equal to the minimum number.

13. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to:
obtain data specifying baseline probability distributions over possible settings for each of a plurality of controllable elements;
maintain a causal model that identifies causal relationships between the possible settings and responses to the possible settings;
repeatedly perform the following:
select, control settings based on the causal model and values for a parameter of the system that are sampled from a range of possible values for the parameter;
select control settings based on the baseline probability distributions;
monitor responses to (i) the control settings selected based on the causal model and (ii) the control settings selected based on the baseline probability distributions;
determine, for each of the possible values of the parameter, a difference between (i) a system performance when the control settings are selected based on the causal model and on the possible value of the parameter and (ii) a system performance measure for the control settings selected based on the baseline probability distributions; and
update how frequently each of the possible values is sampled based on the measures of difference.

14. The system of claim 13 storing instructions further comprising setting a value of a ratio parameter by performing a statistical power analysis to compute a minimum number of baseline instances that are required to determine that hybrid instances outperform the baseline instances with a threshold statistic power.

15. The system of claim 14 storing instructions further comprising adjusting a value of the ratio parameter to be equal to the minimum number.

16. The system of claim 13 , wherein the parameter is a data inclusion window that defines how many previously received environment responses are used to update the causal model.

17. One or more non-transitory computer-readable media storing instructions that when executed by one or more processors cause one or more computers to perform operations comprising:
obtaining data specifying baseline probability distributions over possible settings for each of a plurality of controllable elements;
maintaining a causal model that identifies causal relationships between the possible settings and responses to the possible settings;
repeatedly performing the following:
selecting, control settings based on the causal model and values for a parameter of a system that are sampled from a range of possible values for the parameter;
selecting control settings based on the baseline probability distributions;
monitoring responses to (i) the control settings selected based on the causal model and (ii) the control settings selected based on the baseline probability distributions;
determining, for each of the possible values of the parameter, a difference between (i) a system performance when the control settings are selected based on the causal model and on the possible value of the parameter and (ii) a system performance measure for the control settings selected based on the baseline probability distributions; and
updating how frequently each of the possible values is sampled based on the measures of difference.

18. The one or more non-transitory computer-readable media of claim 17 storing instructions further comprising setting a value of a ratio parameter by performing a statistical power analysis to compute a minimum number of baseline instances that are required to determine that hybrid instances outperform the baseline instances with a threshold statistic power.

19. The one or more non-transitory computer-readable media of claim 18 storing instruc

Assignees

• 3M Innovative Properties Company

Inventors

• Brooks Brian E
• Benoit Gilles J
• Olson Peter O
• Olson Tyler W
• Nayar Himanshu
• Arsenault Frederick J
• Johnson Nicholas A

Classifications

• G05B23/0248

  Causal models, e.g. fault tree; digraphs; qualitative physics · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F18/2193

  based on specific statistical tests · CPC title

• G05B13/021

  in which a variable is automatically adjusted to optimise the performance · CPC title

• B60W40/105

  Speed · CPC title