“Counterfactual Reasoning and Learning Systems”
E367293
“Counterfactual Reasoning and Learning Systems” is a research work by Léon Bottou that explores how to use counterfactual inference to design and analyze machine learning systems, particularly in interactive and decision-making settings.
All labels observed (1)
| Label | Occurrences |
|---|---|
| “Counterfactual Reasoning and Learning Systems” canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T3542940 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “Counterfactual Reasoning and Learning Systems” Context triple: [Léon Bottou, hasPublication, “Counterfactual Reasoning and Learning Systems”]
-
A.
Soar cognitive architecture
The Soar cognitive architecture is a general-purpose framework for modeling and understanding human cognition through unified theories of problem solving, learning, and decision-making.
-
B.
Cambrian intelligence: The early history of the new AI
Cambrian Intelligence: The Early History of the New AI is a book by roboticist Rodney Brooks that outlines his influential behavior-based approach to artificial intelligence and robotics in contrast to traditional symbolic AI.
-
C.
Experience and Prediction
Experience and Prediction is a seminal philosophical work by Hans Reichenbach that develops a logical and probabilistic foundation for scientific knowledge and induction within the framework of logical empiricism.
-
D.
Temporal Logic of Actions
Temporal Logic of Actions is a formal framework for specifying and reasoning about concurrent and distributed systems using temporal logic to describe system behaviors over time.
-
E.
new riddle of induction
The new riddle of induction is Nelson Goodman’s influential philosophical problem that challenges traditional accounts of inductive reasoning by introducing the notion of “grue” and questioning how we justify projecting certain predicates into the future.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: “Counterfactual Reasoning and Learning Systems” Target entity description: “Counterfactual Reasoning and Learning Systems” is a research work by Léon Bottou that explores how to use counterfactual inference to design and analyze machine learning systems, particularly in interactive and decision-making settings.
-
A.
Soar cognitive architecture
The Soar cognitive architecture is a general-purpose framework for modeling and understanding human cognition through unified theories of problem solving, learning, and decision-making.
-
B.
Cambrian intelligence: The early history of the new AI
Cambrian Intelligence: The Early History of the New AI is a book by roboticist Rodney Brooks that outlines his influential behavior-based approach to artificial intelligence and robotics in contrast to traditional symbolic AI.
-
C.
Experience and Prediction
Experience and Prediction is a seminal philosophical work by Hans Reichenbach that develops a logical and probabilistic foundation for scientific knowledge and induction within the framework of logical empiricism.
-
D.
Temporal Logic of Actions
Temporal Logic of Actions is a formal framework for specifying and reasoning about concurrent and distributed systems using temporal logic to describe system behaviors over time.
-
E.
new riddle of induction
The new riddle of induction is Nelson Goodman’s influential philosophical problem that challenges traditional accounts of inductive reasoning by introducing the notion of “grue” and questioning how we justify projecting certain predicates into the future.
- F. None of above. chosen
Statements (44)
| Predicate | Object |
|---|---|
| instanceOf |
machine learning paper
ⓘ
research work ⓘ scientific paper ⓘ |
| addresses |
evaluation bias in interactive systems
ⓘ
exploration–exploitation tradeoff in learning systems ⓘ learning from biased logged data ⓘ safety of deploying new policies ⓘ |
| aimsTo |
bridge causal inference and machine learning practice
ⓘ
enable safe experimentation in production systems ⓘ improve reliability of policy evaluation ⓘ reduce need for online A/B testing ⓘ |
| appliesTo |
ad placement systems
ⓘ
information retrieval systems ⓘ interactive recommendation systems ⓘ online systems ⓘ |
| author | Léon Bottou ⓘ |
| contributesTo |
evaluation methodology for interactive ML
ⓘ
practical design of learning systems ⓘ theory of counterfactual learning ⓘ |
| field |
causal inference
ⓘ
counterfactual reasoning ⓘ interactive learning ⓘ machine learning ⓘ sequential decision making ⓘ |
| focusesOn |
counterfactual inference in learning systems
ⓘ
decision-making systems ⓘ evaluation of system changes using historical data ⓘ interactive machine learning systems ⓘ learning from logged bandit feedback ⓘ off-policy evaluation ⓘ policy optimization ⓘ |
| language | English ⓘ |
| proposesMethod |
doubly robust estimation techniques
ⓘ
importance weighting for counterfactual estimation ⓘ off-policy counterfactual evaluation of policies ⓘ use of counterfactual estimators for system evaluation ⓘ |
| relatedTo |
A/B testing
ⓘ
contextual bandits ⓘ off-policy learning ⓘ reinforcement learning ⓘ |
| usesConcept |
causal effect estimation
ⓘ
potential outcomes ⓘ propensity scores ⓘ randomization in logging policies ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: “Counterfactual Reasoning and Learning Systems” Description of subject: “Counterfactual Reasoning and Learning Systems” is a research work by Léon Bottou that explores how to use counterfactual inference to design and analyze machine learning systems, particularly in interactive and decision-making settings.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.