RLCFR improves CFR's generalization in imperfect information games.
problem Improving CFR's performance in large-scale, imperfect information games.
method RLCFR integrates CFR with deep reinforcement learning to update strategies dynamically.
result RLCFR significantly enhances CFR's generalization ability in various games.
Improved CFR achieves faster convergence to Nash equilibrium.
problem Theoretical slow convergence rate of CFR algorithms.
method Combining predictive and stable regret minimizers within CFR.
result Achieves O ( T − 3 / 4 ) O(T^{-3/4}) O ( T − 3/4 ) convergence rate, faster than O ( T − 1 / 2 ) O(T^{-1/2}) O ( T − 1/2 ) . The paper tackles optimal policy learning with asymmetric counterfactual utilities in healthcare decisions.
problem Learning optimal policies from observed data with asymmetric counterfactual utilities.
method The approach involves identifying and minimizing the maximum expected utility loss using statistical decision theory and solving intermediate classification problems.
result One can learn minimax loss decision rules from observed data.
Paper addresses theoretical risks in neural MCCFR, proposing Robust Deep MCCFR for improved performance.
problem Theoretical risks in neural MCCFR, especially in large games.
method Adaptive framework with selective component deployment, including target networks, exploration, and variance-aware training.
result Robust Deep MCCFR achieves significant exploitability improvements in both Kuhn and Leduc Poker.
Dual behavior policy improves reinforcement learning across various environments.
problem Challenges in reinforcement learning with inconsistent or unknown environments.
method Dual, advantage-based behavior policy using counterfactual regret minimization.
result Demonstrated improved performance over baseline models in diverse environments.
This paper uses counterfactual thinking to improve multi-agent reinforcement learning.
problem Improving decision-making in multi-agent environments.
method Proposes a deep reinforcement learning model with counterfactual thinking to generate and evaluate multiple actions.
result Counterfactual thinking enhances agents' performance in multi-agent environments, leading to higher rewards and fair competition.
DeepRole learns to play hidden role games like Avalon.
problem Learning cooperation in uncertain multi-agent settings.
method Combines CFR and deep learning with deductive reasoning.
result DeepRole outperforms other agents and humans in Avalon.
A new algorithm LONR learns without terminal states or perfect recall.
problem Learning in settings without terminal states or perfect recall.
method Local No-Regret Learning (LONR) using Q-learning-like updates.
result LONR achieves last iterate convergence in challenging settings.
Counterfactual regret minimization (CFR) is the most popular algorithm on solving two-player zero-sum extensive games with imperfect information and achieves state-of-the-art performance in practice. However, the performance of CFR is not fully understood, since empirical results on the regret are much better than the …
New method minimizes decision errors in large treatment spaces.
problem Improving decision-making in large treatment spaces with biased observational data.
method Loss minimizes classification error of actions in large action space.
result Proves improved decision-making performance in large combinatorial action spaces.
ESCHER avoids importance sampling to estimate regret in large games.
problem Estimating Nash equilibria in large games with high variance.
method Computes a history value function to estimate regret without importance sampling.
result ESCHER reduces regret estimation variance significantly compared to existing methods.
New approach uses DRO for better counterfactual risk estimation.
problem Improving counterfactual decision making in uncertain environments.
method Combines Distributionally Robust Optimization with Counterfactual Risk Minimization.
result Proposes Kullback-Leibler divergence for robust counterfactual risk estimation.
Proposes Exogenous Matching for efficient counterfactual estimation.
problem Efficient estimation of counterfactual expressions in general settings.
method Transforms variance minimization into conditional distribution learning.
result Outperforms other importance sampling methods in counterfactual estimation.
Proposes minimal interventions over counterfactual explanations for algorithmic recourse.
problem Lack of actionable recommendations for algorithmic recourse.
method Causal reasoning to shift focus from explanations to recommendations.
result Minimal interventions provide more actionable recommendations for recourse.
Proposes a new method for estimating counterfactual treatment effects.
problem Uncertainty in identifying causal mechanisms from observational data.
method Introduces a parameterized family of causal mechanisms that generalize Gumbel-max, trained to minimize counterfactual effect variance.
result Trained mechanisms yield lower variance estimates of counterfactual treatment effects.
Paper solves learning imperfect-information games with fewer episodes.
problem Learning imperfect-information extensive-form games from bandit feedback.
method Balanced Online Mirror Descent and Balanced Counterfactual Regret Minimization algorithms.
result Achieves near-optimal sample complexity for finding approximate Nash equilibria.
Self-Distilled Disentanglement improves counterfactual predictions by separating variables.
problem Improving counterfactual predictions in the presence of confounders and unobserved variables.
method Self-Distilled Disentanglement framework based on information theory.
result Effective counterfactual inference in synthetic and real-world datasets.
New algorithm reduces bandit regret by graph domination number.
problem Adversarial multi-armed bandit with partial observations and switching costs.
method New algorithm with improved policy regret bounds.
result Regret depends only on the domination number of the feedback graph.
This paper introduces collective counterfactual explanations for groups of instances in classification models.
problem Understanding how classification models make decisions for groups of instances.
method Novel Mathematical Optimization models to find collective counterfactual explanations that minimize total perturbation cost.
result Detects critical features for entire dataset classification and handles outliers.
ACE improves counterfactual explanations with fewer model queries.
problem Inefficient sampling for counterfactual explanations in machine learning models.
method Adaptive sampling combining Bayesian estimation and stochastic optimization.
result ACE achieves superior evaluation efficiency compared to state-of-the-art methods.
New method debiases counterfactual distributions using observational data.
problem Estimating counterfactual distributions under interventions without relying on observational data.
method Flow-matching approach to learn counterfactual distributions from observational data.
result Deconfounding flows outperform existing debiased counterfactual distribution estimators.
Proposes a method to generate realistic counterfactuals by learning relationships.
problem Counterfactual explanations often ignore intrinsic relationships between data attributes.
method Uses a variational auto-encoder to learn relationships and perturb the latent space.
result The model preserves relationships and generates realistic counterfactuals.
Study benchmarks contextual bandit algorithms for precision oncology using in vitro data.
problem Designing effective protocols for individual treatment assignment in precision oncology.
method Proposed a benchmark dataset of in vitro drug responses to evaluate contextual bandit algorithms.
result Bayesian bandit algorithms performed better than a rule-based baseline in minimizing regret.
Introduces PCG for better counterfactual explanations in vision models.
problem Ambiguity in latent-space optimization methods for counterfactual explanations.
method Constructs counterfactuals by tracing geodesics under a perceptually Riemannian metric.
result PCG outperforms baselines and reveals hidden failure modes.
Algorithm improves reinforcement learning in MDPs with partial order policies.
problem Improving reinforcement learning in MDPs with partial order policies.
method Epoch-based reinforcement learning algorithm leveraging a partial order over policy class.
result Achieves an O ( w log ( ∣ Θ ∣ ) T ) O(\sqrt{w \log(|Θ|) T}) O ( w log ( ∣Θ∣ ) T ) regret bound, independent of state and action space sizes. Generative deep learning creates counterfactual states to explain Atari agent decisions.
problem Difficulty in explaining deep reinforcement learning agent decisions to humans.
method Generative deep learning to create counterfactual states.
result Counterfactual states help non-expert participants understand Atari agent decision-making.
Paper proposes algorithms to minimize both dynamic and adaptive regret simultaneously.
problem Traditional regret minimization algorithms are suboptimal for changing environments.
method Developed novel online algorithms to minimize dynamic and adaptive regret simultaneously.
result Proposed algorithms minimize dynamic and adaptive regret over any interval.
Develops methods to improve demand counterfactuals from imperfect proxies.
problem Imperfect proxies in demand models lead to biased counterfactuals and invalid inference.
method Practical toolkit for market-level and individual data, requiring minimal computation.
result Improves substitution prediction and counterfactual performance.
The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge arises by the fact that risk-averse commercial SMT systems deterministically lo…
DECE visualizes machine learning decisions with counterfactual explanations.
problem Making machine learning models transparent and explainable.
method Interactive visualization system supporting counterfactual explanations at instance- and subgroup-levels.
result DECE enables users to explore and understand machine learning model decisions.
Study minimax rates for online learning with time-varying dynamics.
problem Online learning with time-varying state and cost dynamics.
method Non-constructive upper and lower bounds, complexity and stability terms.
result Characterization of minimax rates and necessary conditions for learnability.
G-Net uses deep learning for complex counterfactual outcome prediction.
problem Estimating counterfactual outcomes under dynamic treatment strategies.
method G-Net is a sequential deep learning framework for G-computation.
result G-Net can handle complex temporal data and provide accurate treatment effects.
We present a Bayesian view of counterfactual risk minimization (CRM) for offline learning from logged bandit feedback. Using PAC-Bayesian analysis, we derive a new generalization bound for the truncated inverse propensity score estimator. We apply the bound to a class of Bayesian policies, which motivates a novel, pote…
Regret minimization is a powerful tool for solving large-scale problems; it was recently used in breakthrough results for large-scale extensive-form game solving. This was achieved by composing simplex regret minimizers into an overall regret-minimization framework for extensive-form game strategy spaces. In this paper…
Paper tackles online learning for DR management with incentives.
problem Estimating baseline consumption in DR programs with consumer incentives.
method Online learning scheme using least-squares with perturbed reward prices.
result Achieves low regret of $\mathcal{O}\left((\log{T})^2
ight)$ compared to optimal.
New method predicts outcomes even when some factors are not used in models.
problem Predicting outcomes under runtime confounding where some factors are unavailable.
method Doubly-robust procedure for counterfactual predictions.
result Method often outperforms competing approaches in runtime confounding.
A method removes treatment-covariate dependence for counterfactual prediction without adversarial training.
problem Counterfactual prediction under assignment bias.
method Information-theoretic approach learning a stochastic representation Z to minimize mutual information with outcomes.
result The method performs favorably in likelihood, counterfactual error, and policy evaluation compared to adversarial baselines.
CFRecs uses counterfactual reasoning to improve graph-based recommendations in real estate.
problem Improving model interpretability and actionable insights in graph-based recommender systems.
method A two-stage architecture combining GNN and Graph-VAE to propose minimal yet impactful changes in graph structure and node attributes.
result Demonstrates effectiveness in delivering actionable recommendations for home buyers and sellers.
Proposes a scalable method for counterfactual prediction using machine learning.
problem De-bias causal estimators with high-dimensional data in observational studies.
method Uses entropy balancing to learn weights minimizing Jensen-Shannon divergence, leading to robust counterfactual predictions.
result Consistent causal estimation if either propensity score or outcome model is correctly specified.
Improved active learning for counterfactual learning from observational data.
problem Learning a classifier from observational data with selection bias.
method Active learning with a counterfactual risk minimizer, modifying both risk and active learning process.
result Statistically consistent and more label-efficient algorithm compared to prior work.
New method for estimating counterfactual means in adaptive experiments.
problem Inference for counterfactual means in sequentially designed experiments with adaptive treatment policies.
method Latent factor model and nearest neighbors method for estimation.
result Asymptotically valid confidence intervals for counterfactual means established.
Paper proposes MIM-DRCFR to learn disentangled factors for better treatment effect estimation.
problem Learning disentangled factors precisely for individual-level treatment effect estimation.
method Multi-task learning framework with MI minimization criteria.
result MIM-DRCFR outperforms state-of-the-art methods in treatment effect estimation.
cGAN learns a distribution for causal inference without specifying P.
problem Enforcing strong ignorability in causal analyses of observational data.
method Generative adversarial network (GAN)-based model called the Counterfactual χ χ χ -GAN (cGAN). result Minimizes Pearson χ 2 χ^2 χ 2 divergence, maximizing coverage and minimizing variance of ATE estimates. Study on learning strategies in adaptive Markov games with policy regret as metric.
problem Learning in dynamic Markov games with adaptive opponents is challenging.
method Introduced policy regret as a new learning metric and developed algorithms for consistent adaptive adversaries.
result Achieved T \sqrt{T} T policy regret against certain adaptive adversaries. Survey of counterfactual explanations for time series classification.
problem Generating plausible and actionable counterfactuals for time series data.
method Review of various counterfactual generation methods for time series classification.
result Highlight unique challenges and strengths of existing methods.
Model improves CVR estimation in recommender systems by mitigating bias and overlooking causal relationships.
problem Data sparsity and sample selection bias in CVR estimation.
method Entire Space Counterfactual Multitask Model (ESCM 2 ^2 2 ) incorporating counterfactual risk minimizer. result Significantly enhances recommendation performance by effectively mitigating bias and overlooking causal relationships.
PRINCE provides interpretable explanations for recommender systems by removing minimal user actions.
problem Lack of interpretable explanations for recommender systems.
method PRINCE uses a polynomial-time optimal algorithm based on random walks over dynamic graphs to find minimal user actions that change recommendations.
result PRINCE produces more compact explanations than intuitive baselines and is viable for user understanding.
EMAP finds minimal perturbations to change model predictions, combining feature weighting and counterfactuals.
problem Improving model explanations for black box classifiers.
method Neural network approach that returns minimal adversarial perturbations.
result EMAP provides more interpretable explanations and faster than sampling-based methods.