InfoBot learns decision states from prior experience to guide exploration.
problem Discovering effective policies in sparse reward environments.
method InfoBot uses an information bottleneck to learn decision states from prior experience.
result InfoBot effectively identifies decision states, even in partially observed settings.
Describes state variables in sequential decision problems, linking them to Markovian and non-Markovian models.
problem Sequential decision problems, especially in active learning and POMDPs, where decisions affect what is observed and learned.
method Canonical framework and novel two-agent perspective of POMDPs, defining state variables to claim Markovian or non-Markovian models.
result Properly modeled sequential decision problems are Markovian, while real decision problems are often non-Markovian.
Adversarial attacks on probabilistic state-space models affect latent state and policy decisions.
problem Robust reinforcement learning under adversarial observability.
method Analyzing adversarial attacks on linear probabilistic state-space models.
result Demonstrating the influence of adversarial observations on latent state and policy decisions.
Empirical model tackles decision problems without specifying states of the world.
problem Decision problems under uncertainty with inaccessible states of the world.
method Empirical approach using observed act--consequence pairs as model primitives.
result Optimality in empirical decision problems addressed using protocol-based empirical choice functions.
The paper tackles finding optimal treatment sequences in continuous state spaces.
problem Finding counterfactually optimal action sequences in continuous state spaces.
method Formalizes the problem using finite horizon Markov decision processes and structural causal models. Develops a search method based on the A* algorithm.
result The method can find optimal action sequences in polynomial time under certain conditions.
Simplifies complex RL policies by ranking important decisions.
problem Complexity in RL policies makes them hard to analyze and interpret.
method Statistical fault localisation to rank states and prune unimportant decisions.
result Pruned policies can perform similarly to original policies, improving interpretability.
This paper simplifies OPE in large state spaces using state abstractions.
problem Accurately evaluating policies offline in large state spaces.
method Developed a backward-model-irrelevance condition and an iterative state abstraction procedure.
result Deeply-abstracted states substantially simplify OPE sample complexity.
This paper solves steady-state planning for multichain MDPs.
problem Specifying constraints on the steady-state behavior of an agent.
method Linear programming solution for multichain MDPs.
result Optimal solutions yield stationary policies with rigorous guarantees.
We review two strands of conceptual approaches to the formal representation of a decision maker's non-knowledge at the initial stage of a static one-person, one-shot decision problem in economic theory. One focuses on representations of non-knowledge in terms of probability measures over sets of mutually exclusive and …
Extends reinforcement learning to continuous state spaces with safety constraints.
problem Safety-critical reinforcement learning in continuous state spaces with unknown dynamics.
method Introduces a novel Budgeted Bellman Optimality operator and applies it to continuous state spaces.
result Validated on spoken dialogue and autonomous driving applications.
The paper tackles reward-relevance in offline RL with sparse decision dynamics.
problem Offline reinforcement learning with sparse decision dynamics and estimation sparsity.
method Reward-filtered least-squares policy evaluation using thresholded lasso.
result The method provides theoretical guarantees with sample complexity dependent on sparse component size.
Deep neural network learns discrete state abstractions for efficient planning.
problem Efficient sequential decision making in large state spaces.
method Information bottleneck method for learning approximate bisimulations using deep neural encoders and action-conditioned HMM.
result Trained method efficiently plans for unseen goals in multi-goal reinforcement learning.
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.
Algorithm finds safe zones in policy Markov Decision Processes to limit trajectory escape.
problem Finding safe zones in policy Markov Decision Processes to limit trajectory escape.
method Bi-criteria approximation learning algorithm with polynomial sample complexity.
result Achieves almost 2 approximation for both escape probability and safe zone size.
Sparse oblique decision tree improves security rules for renewable power systems.
problem Identifying secure operating conditions in power systems with high renewable energy.
method Sparse weighted oblique decision tree to learn and embed linear security rules.
result The method significantly increases secure states and reduces solution time.
GNNs often fail to accurately assess their own predictions.
problem GNNs lack calibration for high-stakes decisions.
method Empirical evaluation of GNN calibration on multiple datasets.
result GNNs can be calibrated but often fail, highlighting the need for improvement.
AI learns to design chemical processes efficiently.
problem Designing efficient chemical processes.
method Hierarchical reinforcement learning and graph neural networks.
result Quick learning in various decision spaces.
Develops methods for finding counterfactual explanations in sequential decision making.
problem Finding counterfactual explanations for sequential decision making processes.
method Formal characterization of sequential actions and states using Markov decision processes and Gumbel-Max structural causal model. Introduces a polynomial time algorithm based on dynamic programming.
result Algorithm finds optimal counterfactual explanations for sequential decision making.
The paper uses a novel framework to learn option prices by imitating principal investor behavior.
problem Challenges in modeling stock price changes and decision making in equity markets.
method Non-deterministic Markov decision process, Bayesian deep neural network, reinforcement learning.
result Optimal option prices learned through imitation of principal investor behavior.
The paper analyzes and proposes a new stopping criterion for recursive Bayesian classification.
problem Limitations of conventional stopping criteria in recursive Bayesian classification.
method Geometric interpretation of state posterior progression and analysis of conventional criteria.
result Proposes a new stopping criterion to overcome limitations of conventional methods.
Study how learning impacts decision-making in project expansion.
problem Optimal timing of expansion decisions based on uncertain project profitability.
method Bayesian updating model with two irreversible alternatives (exit or expansion).
result Time-to-decision is not monotonic with information arrival rate.
Decision forests, including Random Forests and Gradient Boosting Trees, have recently demonstrated state-of-the-art performance in a variety of machine learning settings. Decision forests are typically ensembles of axis-aligned decision trees; that is, trees that split only along feature dimensions. In contrast, many r…
We solve a broad class of sequential decision-making problems with partially observed states.
problem Sequential decision-making under uncertainty with partially observed states.
method Modeling as a partially observed Markov decision process (POMDP) and separating state and modulation process.
result The approach allows for specialized approximate solution procedures.
New algorithms approximate state similarity in large MDPs.
problem Computing exact bisimulation metrics in large MDPs is expensive and impractical.
method Developed a new metric tied to behavior policy, and two algorithms for approximating it.
result Presented algorithms that can approximate bisimulation metrics in large, deterministic MDPs.
The paper develops methods to estimate POMDPs from partial information.
problem Making decisions under partial information about state variables.
method Structural estimation of POMDP primitives using observable history.
result Conditions for model identifiability without state dynamics knowledge.
Bayesian framework for learning optimal action-value function in MDPs.
problem Uncertainty quantification in MDPs for optimal decision-making strategies.
method Full Bayesian framework including modelling, inference, and decision-making.
result Demonstrates exploration benefits of posterior sampling in MDPs.
Unified framework models neural decision-making, improving accuracy.
problem Limitations in modeling neural activity during decision-making.
method Unifying framework based on state-space models with scalable inference.
result Two-dimensional accumulator better captures neural responses.
The paper introduces return parity for fairness in MDPs, addressing delayed and adverse effects.
problem Fairness in MDPs for dynamic domains with delayed and adverse effects.
method Proposes return parity, decomposes return disparity, and develops algorithms for state visitation distributional alignment.
result The proposed algorithms can successfully close the disparity gap while maintaining policy performance.
Bayesian framework captures correlations in discrete environments for better decision-making.
problem Capturing correlations in discrete state-action domains for better decision-making.
method Bayesian learning framework based on Pólya-Gamma augmentation.
result Superior predictive performance compared to correlation-agnostic models.
Treant creates evasion-resistant decision trees.
problem Evasion attacks on decision tree ensembles.
method Treant minimizes evasion-aware loss function, using robust splitting and attack invariance.
result Treant generates accurate, nearly evasion-insensitive decision trees.
A new RL paradigm reduces state-action-value function approximation inefficiency.
problem Challenges in state-action-value function approximation for RL.
method State Action Separable Reinforcement Learning (sasRL) decouples action space from value function learning.
result sasRL achieves up to 75% better performance than state-of-the-art MDP-based RL algorithms.
Paper solves POMDPs in continuous time and discrete spaces.
problem Optimal decision making in discrete state and action space systems under partial observability.
method Combining optimal filtering theory and deep learning to solve a Hamilton-Jacobi-Bellman equation.
result Derives a mathematical description and solution approach for continuous-time POMDPs.
The paper introduces a method to learn Markov state abstractions for reinforcement learning.
problem Learning Markov state representations in complex environments.
method The paper introduces a novel set of conditions and a training procedure combining inverse model estimation and temporal contrastive learning.
result The approach learns representations that capture the underlying structure of the domain and improve sample efficiency.
New algorithm learns Markov decision processes from test data.
problem Learning Markov decision processes from limited test data.
method L*-based active learning with sampling.
result Sampling-based algorithm outperforms passive learning.
Paper estimates risks in MDPs using state lumping and SAT, showing its effectiveness.
problem Estimating risks in Markov decision processes with state augmentation.
method State augmentation transformation, isotopic states, and state lumping.
result SAT and state lumping effectively estimate mean-variance and exponential utility risks.
Optimized Q-learning reduces regret in state-aggregated MDPs.
problem Reducing regret in reinforcement learning with state aggregation.
method Optimistic Q-learning applied to fixed-horizon episodic MDPs with aggregated states.
result Regret bound of i l d e O ( H 5 M K + ε H K ) ilde{\mathcal{O}}(\sqrt{H^5 M K} + εHK) i l d e O ( H 5 M K + ε H K ) , independent of states and actions. Improved analysis of UCRL2 with empirical Bernstein inequality reduces exploration-exploitation regret.
problem Exploration-exploitation in communicating Markov Decision Processes.
method Analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B).
result Regret bound of O ~ ( D Γ S A T ) \widetilde{O}(\sqrt{DΓS A T}) O ( D Γ S A T ) for UCRL2B. Paper proposes an HMM-based Q-learning for POMDPs.
problem Q-learning struggles with POMDPs due to incomplete state observation.
method Formulates POMDP estimation as HMM estimation, proposing a recursive algorithm to concurrently estimate POMDP parameters and Q function.
result Algorithm converges to optimal Q function and POMDP parameters.
The study examines robust decision-making in volatile financial markets, finding action robustness is more impactful than uncertainty tolerance.
problem Sequential decision making in high-frequency markets under evolving uncertainty.
method Analyzes two dimensions of robustness: uncertainty tolerance and action robustness, using simulations and empirical evidence.
result Action robustness has a larger impact on profitability than uncertainty tolerance, and excessive robustness can reduce profitability in illiquid markets.
Paper learns meaningful state and action representations from MDP trajectories.
problem Learning good state and action representations from MDP trajectories.
method Tensor decomposition, kernelization, importance sampling, low-Tucker-rank approximation.
result The learned state/action abstractions provide accurate approximations to latent block structures.
We optimize saddle-point problems for large-scale Markov decision processes.
problem Optimizing policies in large-scale Markov decision processes.
method Characterized conditions for convergence and designed an optimization algorithm.
result Our algorithm converges faster and is state-space independent.
In this paper we propose an algorithm that builds sparse decision DAGs (directed acyclic graphs) from a list of base classifiers provided by an external learning method such as AdaBoost. The basic idea is to cast the DAG design task as a Markov decision process. Each instance can decide to use or to skip each base clas…
Algorithm estimates human decision-making in high-dimensional states with finite-time guarantees.
problem Estimating optimal policies and measures of fit in dynamic decision models with high-dimensional state spaces.
method Single-loop estimation algorithm with stochastic gradient steps for reward maximization.
result Algorithm converges to a stationary solution with finite-time guarantees and approximates maximum likelihood sublinearly.
New UCB algorithm for learning PSRs with tractable computation and accuracy.
problem Learning predictive state representations in sequential decision-making problems.
method Proposes a novel UCB-type algorithm with a bonus term to estimate PSRs accurately and efficiently.
result First known UCB-type approach for PSRs with guaranteed model accuracy and computational tractability.
Simple method improves exploration in various decision problems.
problem Improving exploration in sequential decision problems.
method Parameterized Exploration (PE) method that considers time horizon and state of knowledge.
result PE outperforms un-tuned methods in various bandit and decision problem settings.
This work extends HiP-MDPs to robust state abstractions for multi-task and meta-reinforcement learning.
problem Limited observability of state in HiP-MDPs for real-world scenarios with rich observation spaces.
method Inspired by Block MDPs, the work extends HiP-MDPs to enable robust state abstractions for multi-task and meta-reinforcement learning.
result Transfer and generalization bounds based on task and state similarity, and sample complexity bounds that depend on the aggregate number of samples across tasks.
Study links cognitive effort to thermodynamic principles, optimizing decision-making.
problem Understanding the energy cost of decision-making in living systems.
method Applied Landauer's principle to analyze belief dynamics in a two-armed bandit game.
result Cognitive energy cost correlates with optimal decision-making outcomes.
Bayesian GBMs improve predictive uncertainty calibration for tabular data.
problem Lack of well-calibrated predictive uncertainties in gradient boosting machines.
method Variational inference with soft decision trees.
result Variational soft GBMs provide useful uncertainty estimates and maintain good predictive performance.