Paper improves AIRL by enhancing policy imitation and addressing reward recovery issues.
problem Inadequate policy imitation and limited transferable reward recovery in AIRL.
method Substituted built-in algorithm with SAC for policy updating and proposed PPO-AIRL + SAC hybrid framework.
result SAC improves policy imitation but hinders reward recovery; PPO-AIRL + SAC achieves satisfactory transfer effect.
Deep RL trains a robust humanoid push-recovery policy.
problem Training robust humanoid push-recovery policies.
method Model-free Deep Reinforcement Learning.
result Policy learns robust behaviors across the entire body.
New framework for learning policies that converge in out-of-sample regions.
problem Reliable out-of-sample recovery in imitation learning.
method Contractive dynamical systems and recurrent equilibrium networks.
result Policy rollouts converge regardless of perturbations, enabling efficient OOS recovery.
A new method recovers rewards from behavior policies using classification and regression.
problem Recovering meaningful rewards from observed behavior in reinforcement learning.
method GenPQR, a modular procedure that estimates behavior policy, evaluates soft Q-function, and recovers normalized reward using classification and regression.
result GenPQR matches or improves reward recovery compared to DeepPQR, while being simpler and more modular.
CPR models complex decision processes by breaking them into context-specific policies, improving interpretability and accuracy.
problem Interpreting dynamic human decision-making processes in medical contexts.
method Develops Contextualized Policy Recovery (CPR) framework for multi-task learning, modeling each context-specific policy as a linear map.
result Achieves state-of-the-art performance in predicting medical decisions, closing the gap between interpretable and black-box methods.
Efficient algorithms for low-rank bandits using subspace recovery.
problem Contextual bandits with low-rank reward matrices.
method Spectral methods for subspace recovery, reformulating as linear bandits.
result Nearly optimal policy evaluation and best policy identification, minimax guarantees for regret minimization.
Optimizes loan recovery timing by forecasting cash flows.
problem Minimizing overall credit loss in loan portfolios.
method Forecast future cash flows using probabilistic and Markov chain models.
result Empirical illustration of loss-optimal recovery timing.
Paper learns versatile balancing and recovery motions for humanoid robots.
problem Training humanoid robots to handle unexpected perturbations.
method Hierarchical Deep Reinforcement Learning in a physics simulator.
result Learned skills comparable to preprogrammed controllers but more adaptable.
The study analyzes how neural reward models learn features for policy optimization in a Gaussian single-index model.
problem Reward modeling in policy optimization and its impact on downstream value.
method Two-stage neural reward model: first learns hidden direction, then fits readout layer.
result For any feature-learning temperature above a dimension-free threshold, a constant fraction of neurons recover the hidden direction.
Develops CLTs for Markov chain transition probabilities and policies.
problem Estimating transition probabilities and policies in controlled Markov chains.
method Non-parametric estimator for transition matrices; CLTs for value, Q-, and advantage functions; goodness-of-fit tests.
result Asymptotic normality of estimators under specific logging policies.
Proposes a fusion method for many treatment groups in ITRs.
problem Challenges in handling many treatment groups with data sparsity and covariate imbalance.
method Calibration-weighted treatment fusion procedure that balances covariates and fuses similar treatments.
result Ensures robust treatment group recovery and policy value compared to existing methods.
Joint replacement is the most common inpatient surgical treatment in the US. We investigate the clinical pathway optimization for knee replacement, which is a sequential decision process from onset to recovery. Based on episodic claims from previous cases, we view the pathway optimization as an intelligence crowdsourci…
Optimizes loan recovery timing across various portfolios.
problem Comparing and evaluating bank's loan recovery decision rules.
method Simulation-based expert system considering time value of money and costs.
result Threshold optima exist across different risk scenarios and portfolio compositions.
A deep model learns to stop early based on variational stopping policy.
problem Varying optimal depth for different inputs in deep architectures.
method A steerable architecture learns a feed-forward deep model and a variational stopping policy together.
result The learned deep model and stopping policy improve diverse tasks.
C-kNN-LSH identifies similar patient histories for causal inference in longitudinal data.
problem Estimating causal effects from longitudinal trajectories with high-dimensional confounding.
method C-kNN-LSH uses locality-sensitive hashing to find clinical twins and estimate treatment effects.
result C-kNN-LSH outperforms existing methods in capturing recovery heterogeneity and estimating policy values.
New algorithm balances personalization and statistical validity in MRTs.
problem Optimizing decisions in nonstationary settings with habituation and recovery.
method ROGUE-TS Thompson Sampling with probability clipping.
result Achieves lower regret and maintains high statistical power.
New method recovers diverse policies from expert data using state-action pair weighting.
problem Recovering diverse policies from expert trajectories.
method Pointwise mutual information weighted behavioral cloning.
result Effective in focusing on state-action pairs most representative of the style.
We propose a flexible method for estimating value functions in reinforcement learning without parametric assumptions.
problem Lack of interpretability in reinforcement learning models, especially in healthcare applications.
method Nonparametric additive model using local kernel regression and basis expansion.
result Personalized, adaptive recommendations for postoperative recovery.
New framework optimizes multi-asset portfolio choice for high dimensions.
problem Optimizing high-dimensional continuous-time portfolio choice.
method Combines Pontryagin's Maximum Principle with BPTT for neural network policy learning.
result Achieves near-optimal policies with improved efficiency and precision.
Bootstrap method for Markov chains in reinforcement learning.
problem Distributional consistency in finite controlled Markov chains with unknown control policies.
method Model-based bootstrap with novel LLN and CLT for visitation counts and transition increments.
result Asymptotically valid confidence intervals for value and Q-functions in offline RL. This study develops a dynamic inverse optimization framework to recover hidden, time-varying preferences from observed allocation trajectories.
problem The gap between classical optimization theory and real-world practice, especially in the presence of drift and shocks.
method Dynamic inverse optimization framework using a drift-aware estimator grounded in convex analysis and online learning theory.
result Sharp static and dynamic regret bounds for the framework, demonstrating its responsiveness to gradual drift and sudden shocks.
A new framework for adaptive behavior using reusable value profiles.
problem Adaptive behavior in changing environments requires switching among value-control regimes, but maintaining separate parameters for each situation is impractical.
method Introduces value profiles: reusable bundles of parameters assigned to hidden states, allowing for state-conditional strategy recruitment without independent parameters for each context.
result Profile-based models outperform simpler alternatives in probabilistic reversal learning, suggesting belief-dependent control of adaptive behavior.
A contraction analysis improves model-based RL's error recovery.
problem Theoretical understanding of model-based reinforcement learning.
method Contraction analysis applied to both stochastic and deterministic state transitions.
result Error reduction in cumulative reward using branched rollouts.
DFPV improves PCL for confounded bandit policy evaluation.
problem Estimating causal effects in confounded settings with high-dimensional data.
method Deep feature proxy variable method (DFPV) for high-dimensional, nonlinear relationships.
result DFPV outperforms state-of-the-art methods on synthetic benchmarks and confounded bandit problems.
Reinforcement learning mimics expert behavior.
problem Learning from expert demonstrations in reinforcement learning.
method Reduction to reinforcement learning with a stationary reward.
result Expert reward can be recovered and imitation learning is bounded.
Unified analysis of reweighted least-squares algorithms for linear models.
problem Recovering unknown signals from linear measurements using reweighted least squares.
method Unified asymptotic analysis of IRLS, lin-RFM, and alternating minimization algorithms.
result The algorithms can achieve favorable performance in a few iterations with appropriate reweighting.
A new method estimates multi-dimensional value distributions using Hilbert space embeddings.
problem Estimating value distributions in complex, multi-dimensional reinforcement learning settings.
method Hilbert space mappings and kernel mean embeddings to estimate the kernel mean embedding of multi-dimensional value distributions.
result Uniform convergence guarantees and robust off-policy evaluation demonstrated in simulations.
Epidemiological model updates infection rates in China, US, Italy.
problem Evaluate policy interventions for mitigating the 2019-nCov pandemic.
method Custom SITR model with variational data assimilation for real-time updates.
result Model robust to initial conditions, infers infection numbers and parameters.
Machine learning has been widely applied to various applications, some of which involve training with privacy-sensitive data. A modest number of data breaches have been studied, including credit card information in natural language data and identities from face dataset. However, most of these studies focus on supervise…
We derive an arbitrage free relationship between recovery swap rates, digital default swap spreads and conventional CDS spreads, and argue that the fair forward recovery rate used in recovery swaps must contain a convexity premium over the expected recovery value.
Optimizes bank capital structure under Basel III constraints, simplifying complex dynamics.
problem Optimizing risky investments, dividends, and capital structure under Basel III constraints.
method Formulated as a stochastic control problem, reducing dynamics to a one-dimensional process in leverage ratio.
result Simple policy: pay dividends at an upper barrier and recapitalize at the distress boundary.
The study proves necessary conditions for robust decision-making in uncertain environments.
problem Conditions for robust decision-making in uncertain environments.
method Quantitative selection theorems and binary betting decisions.
result World models, belief-like memory, and persistent variables are necessary for strong task performance.
Method uses Seq2Seq learning to automatically generate recovery commands for ICT systems.
problem Manual decision-making for recovery commands is time-consuming and error-prone.
method Seq2Seq neural network model trained on past logs and commands.
result The model can estimate accurate recovery commands from new failures.
A new model explains U- and Swoosh-shaped stock price recovery during the COVID-19.
problem Modeling stock price recovery during the COVID-19 with V- and L-shaped recovery.
method Introducing a sentiment variable θ to quantify investor sentiment and simulate U- and Swoosh-shaped recovery. result The model explains U- and Swoosh-shaped recovery of sectoral indices with positive sentiment.
This paper improves support recovery in universal one-bit compressed sensing.
problem Support recovery in one-bit compressed sensing for sparse signals.
method Proposes approximate support recovery and superset recovery algorithms with polynomial-time complexity.
result Achieves improved support recovery with fewer measurements compared to existing methods.
This work provides a guaranteed tensor recovery method by combining low-rankness and smoothness priors.
problem Guaranteed tensor recovery with theoretical guarantees for low-rank and smoothness priors.
method Developed a new regularization term that combines low-rankness and smoothness priors, proving exact recovery guarantees.
result Rigorously proved exact recovery guarantees for tensor completion and tensor robust principal component analysis.
New theorems show agents need specific internal structures to perform well under uncertainty.
problem How do agents need to be structured to perform well under uncertainty?
method Proved selection theorems showing strong task performance forces specific internal structures.
result Strong task performance forces world models, belief-like memory, and persistent regime-tracking variables.
We discuss a general notion of "sparsity structure" and associated recoveries of a sparse signal from its linear image of reduced dimension possibly corrupted with noise. Our approach allows for unified treatment of (a) the "usual sparsity" and "usual ℓ1 recovery," (b) block-sparsity with possibly overlapping blo…
We consider the problem of signal recovery on graphs as graphs model data with complex structure as signals on a graph. Graph signal recovery implies recovery of one or multiple smooth graph signals from noisy, corrupted, or incomplete measurements. We propose a graph signal model and formulate signal recovery as a cor…
IRKSN algorithm achieves sparse recovery with wider applicability conditions.
problem Sparse recovery challenges due to NP-hard nature and restrictive conditions.
method IRKSN algorithm based on k-support norm regularizer. result Achieves sparse recovery with explicit constants and standard linear rate.
DAGR improves navigation by refining goal representations conditioned on the current state.
problem Goal-conditioned reinforcement learning lacks state awareness, leading to inefficient policy recovery.
method DAGR refines static goal embeddings into state-conditioned ones using gated cross-attention with a state-goal discrepancy map.
result DAGR improves navigation tasks on OGBench, matching or outperforming base methods.
Higher-order tensors can represent scores in a rating system, frames in a video, and images of the same subject. In practice, the measurements are often highly quantized due to the sampling strategies or the quality of devices. Existing works on tensor recovery have focused on data losses and random noises. Only a few …
In recent years research on credit risk modelling has mainly focused on default probabilities. Recovery rates are usually modelled independently, quite often they are even assumed constant. Then, however, the structural connection between recovery rates and default probabilities is lost and the tails of the loss distri…
Study optimal portfolio selection with Recovery Average Value at Risk, showing better control over liabilities.
problem Optimizing portfolios with a new risk measure under known or uncertain distributions.
method Existence results for mean-risk optimal portfolios under different distributional assumptions.
result Portfolio selection under Recovery Average Value at Risk provides better control over liabilities.
The paper improves conditions for unique recovery in homomorphic sensing of subspaces.
problem Unique recovery of points in a linear subspace from their images under linear maps.
method Tighter and simpler conditions for unique recovery in single and subspace arrangement cases, extending to noise stability.
result Conditions for unique recovery in homomorphic sensing are improved and unified.
HSNLD solves robust Hankel recovery efficiently and robustly.
problem Robust Hankel recovery of sparse outliers and missing entries.
method Hankel Structured Newton-Like Descent (HSNLD) algorithm.
result HSNLD achieves linear convergence independent of the condition number.
Paper analyzes AIRL in high-dimensional spaces using random matrix theory.
problem AIRL's performance challenges in high-dimensional environments.
method Examined the rank of the matrix derived from transition matrix, applied random matrix theory.
result High-dimensional scenarios reveal transfer limitations not inherent to AIRL framework.
New method improves dictionary recovery from over-realized models.
problem Theoretical guarantees for model recovery in dictionary learning are limited.
method Search over larger over-realized models to facilitate dictionary recovery.
result Model recovery can be upper-bounded by empirical risk and generalization gap.