UTE improves reinforcement learning by measuring action uncertainty, enhancing policy learning efficiency.
problem Degrading performance of action repetition in reinforcement learning, especially with sub-optimal actions.
method UTE uses ensemble methods to measure uncertainty during action extension, allowing strategic exploration or certainty.
result UTE outperforms existing action repetition algorithms, significantly enhancing policy learning efficiency.
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.
Q-Distribution Guided Q-Learning corrects overestimation of uncertain OOD actions in offline RL.
problem Overestimation of Q-values for out-of-distribution actions in offline reinforcement learning.
method QDQ applies a pessimistic adjustment to Q-values in uncertain OOD regions based on a consistency model.
result QDQ improves performance on the D4RL benchmark and achieves significant improvements across many tasks.
A new RL method using SSD compares action uncertainties to manage aleatoric uncertainty.
problem Managing aleatoric uncertainty in RL environments.
method Distributional RL based on SSD, mapping to Wasserstein gradient flow.
result Optimal particle-based algorithm for SSD policy demonstrates better uncertainty balancing.
This work formalizes robustness criteria for reinforcement learning actions and improves performance in perturbed environments.
problem Improving reinforcement learning policies to perform well in uncertain or adversarial action scenarios.
method Formalized two robustness criteria for reinforcement learning actions, considering adversarial actions and action perturbations. Developed algorithms for tabular and deep reinforcement learning settings.
result Action-robust reinforcement learning policies improve performance in perturbed environments and are a form of implicit regularization.
Study proves duality in exotic option pricing under uncertain model and delayed information.
problem Pricing and hedging of multi-action exotic options under nondominated model uncertainty and delayed information.
method Reformulated superhedging problem as a European option problem, proving duality results.
result Superhedging price equals model-based price with future look-up power.
Study optimal offline RL with uncertainty sets and distribution shifts.
problem Optimal offline reinforcement learning with limited data.
method Construct uncertainty sets and distribution shifts, solve robust Markov decision process.
result Least conservative estimator for unknown true distribution.
Proposes a method to quantify and explain deep learning model uncertainties.
problem Deep learning model predictions are sensitive to perturbations and adversarial attacks.
method Gradient-based uncertainty attribution method to identify problematic regions and propose mitigation strategies.
result Proposed UA-Backprop method achieves competitive accuracy and efficiency compared to existing methods.
Study reduces complexity and uncertainty in human atrial cell models.
problem Uncertainty in parameter estimates from gating kinetics models.
method Approximate Bayesian computation to re-calibrate models, investigate two approaches: more complete datasets and less complex formulations.
result Less complex model with fewer parameters gives better fit and lower uncertainty.
Enhances PlaNet for better planning in uncertain environments.
problem Improving deep planning networks for partially observable environments.
method Incorporates Bayesian inference to handle uncertainty in latent models and action candidates.
result Consistently improves asymptotic performance on continuous control tasks.
New RL algorithm learns good actions from offline data, reducing uncertainty and divergence.
problem Limited applicability of current RL algorithms in real-world settings due to high costs of exploration.
method Proposes an algorithm for batch RL using a fixed offline dataset, with penalties for policy and value constraints.
result Compared favorably to state-of-the-art methods on 32 continuous-action benchmarks.
This work improves neural network trustworthiness through uncertainty estimation.
problem Overconfident neural networks lead to poor performance under distribution shifts.
method Develops a general uncertainty framework for neural networks, including classification with rejection.
result Improves model trustworthiness and robustness in decision-making tasks.
In statistical dialogue management, the dialogue manager learns a policy that maps a belief state to an action for the system to perform. Efficient exploration is key to successful policy optimisation. Current deep reinforcement learning methods are very promising but rely on epsilon-greedy exploration, thus subjecting…
Proposes a method to enhance exploration in RL using temporal difference uncertainties.
problem Challenges in estimating uncertainty in non-tabular reinforcement learning settings.
method Estimates uncertainty over value function using temporal difference errors and incorporates it as an intrinsic reward.
result Demonstrates improved exploration in various tasks, including Deep Sea and Atari 2600 environments.
TS-RSR improves batch Bayesian Optimization by minimizing redundancy and focusing on high uncertainty points.
problem Efficient batch selection in Bayesian Optimization to reduce redundancy and improve performance.
method TS-RSR uses Thompson Sampling to minimize a regret to uncertainty ratio for batch selection.
result TS-RSR outperforms state-of-the-art batch BO algorithms on various test functions.
A method for Bayes-Adaptive Deep RL using meta-learning.
problem Maximizing expected return in unknown environments with uncertainty.
method variBAD: meta-learning for approximate inference and task uncertainty.
result variBAD achieves higher online return than existing methods in MuJoCo domains.
Deep Reinforcement Learning improves with Weighted Q-Learning to reduce bias and uncertainty.
problem Overestimation and high variance in Q-Learning cause learning algorithms to diverge in complex environments.
method Deep Weighted Q-Learning (Deep WQL) uses Dropout and Monte Carlo sampling to approximate WQL's weights and reduce bias.
result Deep WQL reduces bias and improves performance on benchmarks compared to existing methods.
New method disentangles perceptual uncertainty and behavioral costs in partially observable systems.
problem Tackles inverse optimal control for non-linear partially observable systems.
method Probabilistic approach using maximum causal entropy formulations and local linearization.
result Disentangles perceptual factors and behavioral costs in sequential decision-making.
Develops optimal uncertainty quantification for risk-averse decision makers.
problem Quantifying prediction uncertainty for risk-sensitive domains.
method Decision-theoretic foundations connecting uncertainty quantification with risk-averse decision-making.
result Risk-Averse Calibration (RAC) algorithm provides optimal prediction sets for risk-averse decision makers.
Paper presents an efficient exploration method for reinforcement learning.
problem Efficient exploration in reinforcement learning with uncertainty quantification.
method Parameterized Indexed Value Function (PIV) using index sampling.
result Proves the regret bound for learning PIV in a tabular setting and proposes PINs for computational learning.
CRC method provides tighter uncertainty intervals for CT images.
problem Expressing uncertainty in CT images in clinically meaningful terms.
method Semantically adaptive CRC procedure leveraging length minimization.
result Valid coverage of ground-truth images with tighter uncertainty intervals.
Agent uses message passing to optimize robot navigation, balancing exploration and exploitation.
problem Optimizing robot navigation in continuous-valued spaces with uncertainty.
method Autoregressive active inference agent using message passing on a factor graph.
result Agent modulates action based on predictive uncertainty, leading to better model of dynamics.
This paper studies directed exploration for reinforcement learning agents by tracking uncertainty about the value of each available action. We identify two sources of uncertainty that are relevant for exploration. The first originates from limited data (parametric uncertainty), while the second originates from the dist…
BCPO optimizes offline RL policies by converting uncertainty into conservative bounds.
problem Offline RL's fragility under distribution shifts and model errors.
method Bayesian approach with credible lower bounds and KL regularization.
result BCPO yields an uncertainty-calibrated policy that avoids exploiting model errors.
This study evaluates methods to measure traffic forecasting model confidence.
problem Lack of consensus on uncertainty types and techniques for traffic forecasting models.
method Reviews and compares different uncertainty estimation techniques using real traffic data.
result Empirical evidence shows benefits and caveats of various techniques.
Estimating how uncertain an AI system is in its predictions is important to improve the safety of such systems. Uncertainty in predictive can result from uncertainty in model parameters, irreducible data uncertainty and uncertainty due to distributional mismatch between the test and training data distributions. Differe…
QUAM improves uncertainty quantification in deep learning models.
problem Estimating epistemic uncertainty in deep learning models.
method QUAM identifies regions with high divergence between predictions and a reference model.
result QUAM has lower approximation error of epistemic uncertainty compared to previous methods.
Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally …
Proposes a new method to calibrate uncertainty estimates in deep learning models.
problem Poorly calibrated uncertainty estimates in deep learning models.
method Repurposes heteroscedastic regression as a surrogate for calibration.
result Eliminates the need for recalibration and regularizes the training process.
We solve offline learning problems without action probabilities using imitation and policy improvement.
problem Offline learning in automated decision systems with missing action probabilities.
method We use policy improvement and imitation regularization to estimate action policies.
result Our method improves upon existing approaches by reducing uncertainty and improving accuracy.
In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many situations it is preferable to delay a decision rather than run the risk of making …
RRPI improves offline RL by optimizing policies against worst-case dynamics.
problem Offline RL's performance degrades under distribution shift and transition uncertainty.
method Formulates offline RL as robust policy optimization, treating transition kernel as decision variable.
result RRPI achieves strong average performance on D4RL benchmarks, outperforming recent baselines.
Paper uses subjective logic to estimate uncertainty in multi-armed bandit problems.
problem Estimating uncertainty in multi-armed bandit problems.
method Formalism of subjective logic applied to multi-armed bandits, proposing new algorithms.
result Subjective logic quantities enable useful assessment of uncertainty.
Risk Advisor predicts and mitigates ML deployment failures.
problem Predicting and mitigating test-time failure risks of ML systems.
method Post-hoc meta-learner for estimating failure risks and uncertainties.
result Reliably predicts deployment-time failure risks across various ML models.
Two-step conformal prediction method for adaptive bounding box uncertainties in multi-object detection.
problem Quantifying predictive uncertainty for multi-object detection in safety-critical applications.
method Developed a two-step conformal prediction approach to propagate uncertainty in predicted class labels into bounding box uncertainties, ensuring coverage for incorrectly classified objects.
result Desired coverage levels are satisfied with practically tight predictive uncertainty intervals on real-world datasets.
Regularizes predictions to encourage beneficial user actions.
problem Learning models affect user actions, but provide no guarantees.
method Introduces look-ahead regularization to anticipate and encourage beneficial actions.
result Effective in promoting beneficial user actions in real and synthetic data.
We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past acti…
Develops optimal decision-making framework for uncertain counterfactuals.
problem Ensuring reliability of predictions in high-stakes decisions.
method Policy-Coupled Risk-Averse Conformal Prediction (PC-RACP).
result Optimal prediction sets for counterfactual decisions with valid coverage.
UA-LQE improves value function learning by selectively erasing uncertain entries in Q-matrix.
problem Improving value function learning in complex reinforcement learning tasks.
method Uncertainty-aware low-rank Q-matrix estimation (UA-LQE) algorithm.
result UA-LQE selectively erases uncertain entries in Q-matrix to improve value function approximation.
Mixed RL improves RL efficiency with dual representations.
problem Poor sampling efficiency in RL methods.
method Uses dual representations of environmental dynamics to search optimal policies.
result Proves convergence and recursive stability of the mixed RL.
Solves action selection for large spaces in RL, achieving near-optimal performance.
problem Selecting a small, representative subset of actions from a large, shared action space.
method Extends meta-bandit approach to MDPs, using a relaxed sub-Gaussian process model.
result Achieves performance comparable to full action space, with theoretical guarantees.
A new Bayesian MBRL method improves performance in robotics tasks.
problem Enhancing model-based reinforcement learning with uncertainty.
method Introduces variational inference MPC and probabilistic action ensembles with trajectory sampling (PaETS).
result Consistently improves performance on challenging locomotion tasks.
Bayesian inference over admissible histories leads to irreversible kinetics.
problem Modeling irreversible processes in systems with uncertain histories.
method A Gibbs-type measure weighted by energy-dissipation action and observation constraints, interpreted as a Bayesian posterior.
result The measure concentrates on maximum-a-posteriori (MAP) histories, recovering classical deterministic evolution.
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.
Study finds uncertainty estimators weakly correlate with LLM hallucinations.
problem Characterizing the relationship between uncertainty estimators and LLM hallucinations.
method Systematic empirical study of diverse uncertainty estimators across hallucination types and benchmarks.
result Uncertainty estimators weakly correlate with LLM hallucinations, depending on hallucination type and LLM.
The paper shows how demographic data can lead to biased predictions, proposing 'Affirmative Information' as a solution.
problem Bias in predictions due to demographic data.
method Characterization of error types and conditions leading to disparate impact.
result Demographic variables in data can lead to biased predictions, with higher average outcomes receiving higher false positive rates.
Wrapper improves black-box model auditability and decision trustworthiness.
problem Lack of transparency and auditability in machine learning models used in complex applications.
method Integrates uncertainty measures into black-box models to enhance auditability and decision trustworthiness.
result Improves trust in machine learning models by providing actionable mechanisms to reject uncertain predictions.
Proposes a new metric to evaluate uncertainty in deep learning predictions.
problem Evaluating the reliability of deep learning predictions, especially uncertainty.
method Develops a novel metric for evaluating relative uncertainty in regression tasks with deep neural networks.
result Validates the new metric on a toy dataset and applies it to monocular depth estimation.