Counterfactual Quotient Models: Learning What Actions Change, Not What the World Does

• URL: http://arxiv.org/abs/2608.22092v1
• Date: Sat, 22 Aug 2026 19:55:57 GMT
• Title: Counterfactual Quotient Models: Learning What Actions Change, Not What the World Does
• Abstract summary: Reinforcement-learning models commonly predict complete future states, observations, or feature occupancies.<n>We introduce the Counterfactual Quotient Model, which treats action-conditioned futures as equivalent when they differ only by a component shared across actions.
• Score: 14.67340173071927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement-learning models commonly predict complete future states, observations, or feature occupancies, even though action selection depends only on differences between the consequences of candidate actions. As a result, these models may devote substantial statistical and representational capacity to high-dimensional phenomena that evolve independently of the agent's current choice. We introduce the Counterfactual Quotient Model, which treats action-conditioned futures as equivalent when they differ only by a component shared across actions. Its canonical centered representation removes this common component while preserving every pairwise action comparison expressible by the modeled reward family. The implemented model learns these action-dependent effects directly from synchronized counterfactual rollouts, so shared stochastic dynamics cancel before function approximation rather than after complete futures have been predicted. We establish the decision sufficiency, identifiability, common-mode invariance, approximation behavior, and regret properties of the resulting representation. Controlled experiments in physics-based environments provide initial evidence for these properties: direct effect learning suppresses action-independent variation, supports previously unseen reward queries, and improves action ranking relative to models trained to predict absolute futures.

Related papers

• Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model [67.84198127797005]
  Inverse decision modeling infers latent properties of decision processes from observed behavior.<n>We propose a factorized inverse decision model (FIDM) that decomposes each individual's task-execution likelihood into an action factor and an effort factor.
  arXiv  Detail & Related papers  (2026-08-10T07:46:13Z)
• Function-Valued Causal Influence in Nonlinear Time Series [0.0]
  Causal discovery in time series is increasingly performed using nonlinear machine-learning models, yet the resulting causal relationships are almost always summarized by scalar edge scores.<n>We argue that this practice obscures the true object learned by nonlinear autoregressive models: a state-dependent function whose effect varies across regimes, magnitudes, and contexts.<n>We formalize function-valued causal influence for additive, contribution-decomposable architectures and show that scalar causal scores constitute a severe information bottleneck.
  arXiv  Detail & Related papers  (2026-05-26T00:34:49Z)
• Active inference and artificial reasoning [36.949648744325046]
  This technical note considers the sampling of outcomes that provide the greatest amount of information about the structure of underlying world models.<n>We focus on the sample efficiency afforded by seeking outcomes that resolve the greatest uncertainty about the world model.
  arXiv  Detail & Related papers  (2025-12-24T11:59:36Z)
• Understanding the Implicit Biases of Design Choices for Time Series Foundation Models [90.894232610821]
  Time series foundation models (TSFMs) are a class of potentially powerful, general-purpose tools for time series forecasting and related temporal tasks.<n>Their behavior is strongly shaped by subtle inductive biases in their design.<n>We show how these biases can be intuitive or very counterintuitive, depending on properties of the model and data.
  arXiv  Detail & Related papers  (2025-10-22T04:42:35Z)
• Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors [61.92704516732144]
  We show that the most robust features for correctness prediction are those that play a distinctive causal role in the model's behavior.<n>We propose two methods that leverage causal mechanisms to predict the correctness of model outputs.
  arXiv  Detail & Related papers  (2025-05-17T00:31:39Z)
• An Experimental Study on the Rashomon Effect of Balancing Methods in Imbalanced Classification [0.0]
  This paper examines the impact of balancing methods on predictive multiplicity using the Rashomon effect. It is crucial because the blind model selection in data-centric AI is risky from a set of approximately equally accurate models.
  arXiv  Detail & Related papers  (2024-03-22T13:08:22Z)
• Revisiting Demonstration Selection Strategies in In-Context Learning [66.11652803887284]
  Large language models (LLMs) have shown an impressive ability to perform a wide range of tasks using in-context learning (ICL) In this work, we first revisit the factors contributing to this variance from both data and model aspects, and find that the choice of demonstration is both data- and model-dependent. We propose a data- and model-dependent demonstration selection method, textbfTopK + ConE, based on the assumption that textitthe performance of a demonstration positively correlates with its contribution to the model's understanding of the test samples.
  arXiv  Detail & Related papers  (2024-01-22T16:25:27Z)
• Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities [17.082695183953486]
  A popular workaround is to train a robust model by re-weighting training examples based on a secondary biased model. Here, the underlying assumption is that the biased model resorts to shortcut features. We introduce a fine-tuning strategy that incorporates the similarity between the main and biased model attribution scores in a Product of Experts loss function.
  arXiv  Detail & Related papers  (2023-02-06T15:21:41Z)
• On the Impact of Temporal Concept Drift on Model Explanations [31.390397997989712]
  Explanation faithfulness of model predictions in natural language processing is evaluated on held-out data from the same temporal distribution as the training data. We examine the impact of temporal variation on model explanations extracted by eight feature attribution methods and three select-then-predict models across six text classification tasks.
  arXiv  Detail & Related papers  (2022-10-17T15:53:09Z)
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective [72.55093886515824]
  We introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables. We devise a modular architecture that factorizes the representations of invariant mechanisms and style confounders to approximate a causal graph. Experiment results on synthetic and real datasets show that our three proposed components significantly improve the robustness and reusability of the learned motion representations.
  arXiv  Detail & Related papers  (2021-11-29T18:59:09Z)
• You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction [52.442129609979794]
  Recent deep learning approaches for trajectory prediction show promising performance. It remains unclear which features such black-box models actually learn to use for making predictions. This paper proposes a procedure that quantifies the contributions of different cues to model performance.
  arXiv  Detail & Related papers  (2021-10-11T14:24:15Z)
• Plinko: A Theory-Free Behavioral Measure of Priors for Statistical Learning and Mental Model Updating [62.997667081978825]
  We present three experiments using "Plinko", a behavioral task in which participants estimate distributions of ball drops over all available outcomes. We show that participant priors cluster around prototypical probability distributions and that prior cluster membership may indicate learning ability. We verify that individual participant priors are reliable representations and that learning is not impeded when faced with a physically implausible ball drop distribution.
  arXiv  Detail & Related papers  (2021-07-23T22:27:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.