arXiv research

A new algorithm for deep Q-learning with robustness to state transition uncertainty.

Improved simulation of phase transitions using hierarchical autoregressive networks.

A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In prior works, transitions are uniformly sampled at random from the replay buffer o…

The paper tackles robust control for insurance contracts under uncertain transition rates.

RRPI improves offline RL by optimizing policies against worst-case dynamics.

Paper proposes a new framework for robust multi-modal data fusion under uncertainty.

Proposes a method to enhance exploration in RL using temporal difference uncertainties.

A Robust Markov Decision Process (RMDP) is a sequential decision making model that accounts for uncertainty in the parameters of dynamic systems. This uncertainty introduces difficulties in learning an optimal policy, especially for environments with large state spaces. We propose two algorithms, RTD-DQN and Deep-RoK, …

The paper stabilizes PD term structures under forecast uncertainty using a Kalman filter with an anchored observation model.

Study online RL with mismatched dynamics, achieving sublinear regret.

Deep state space model forecasts time series with uncertainty.

Optimizes state monitoring in Markovian systems with cost constraints.

Paper develops a new RL method for MDPs with uncertainty, achieving better regret bounds.

Improves robust transfer learning with side information.

A new framework for robust policy learning in MDPs with linear mixture dynamics.

MetaCURL tackles non-stationary MDPs with optimal dynamic regret.

Minimum energy paths for transitions such as atomic and/or spin rearrangements in thermalized systems are the transition paths of largest statistical weight. Such paths are frequently calculated using the nudged elastic band method, where an initial path is iteratively shifted to the nearest minimum energy path. The co…

Regularization helps resolve ambiguity in mean-variance models, improving predictive uncertainty quantification.

Novel framework for risk-sensitive reinforcement learning with robustness against uncertainty.

Safe reinforcement learning framework using optimal transport for robustness.

Bayesian ANN method predicts chaotic systems with uncertainty.

New theorems show agents need specific internal structures to perform well under uncertainty.

The study shows how trade uncertainty affects stock-bond correlations over time.

Physics-constrained GP predicts material states under shockwave conditions.

Graph Kalman filters adapt classical filters to graph data.

The goal of system identification is to learn about underlying physics dynamics behind the time-series data. To model the probabilistic and nonparametric dynamics model, Gaussian process (GP) have been widely used; GP can estimate the uncertainty of prediction and avoid over-fitting. Traditional GPSSMs, however, are ba…

This paper presents several models addressing optimal portfolio choice, optimal portfolio liquidation, and optimal portfolio transition issues, in which the expected returns of risky assets are unknown. Our approach is based on a coupling between Bayesian learning and dynamic programming techniques that leads to partia…

A method for robust reinforcement learning in large state spaces.

The study proves necessary conditions for robust decision-making in uncertain environments.

Develops a deterministic method to approximate NSDEs for better uncertainty quantification.

We introduce imprecise Markov semigroups to handle uncertainty in Markov processes.

State entropy regularization improves robustness in reinforcement learning, especially under structured perturbations.

Robots can rapidly acquire new skills from demonstrations. However, during generalisation of skills or transitioning across fundamentally different skills, it is unclear whether the robot has the necessary knowledge to perform the task. Failing to detect missing information often leads to abrupt movements or to collisi…

A Longitudinal Attribute-Conditioned Neural Network (LANTERN) framework for modeling health-state transition probabilities in irregular longitudinal data.

This research improves dynamical systems understanding by identifying latent states and their nonlinear transitions.

Prob-GNN quantifies travel demand uncertainty with deep learning.

New model of vague knowledge without strict partitions or transitivity.

Despite the recent popularity of deep generative state space models, few comparisons have been made between network architectures and the inference steps of the Bayesian filtering framework -- with most models simultaneously approximating both state transition and update steps with a single recurrent neural network (RN…

To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-…

Study identifies transitions between traffic modes on Cologne motorways.

Autoregressive feedback is considered a necessity for successful unconditional text generation using stochastic sequence models. However, such feedback is known to introduce systematic biases into the training process and it obscures a principle of generation: committing to global information and forgetting local nuanc…

Study improves reinforcement learning for stable long-term performance.

A framework combining HSMM and survival analysis for lifecycle-oriented mobility analysis.

Trial-and-error based reinforcement learning (RL) has seen rapid advancements in recent times, especially with the advent of deep neural networks. However, the majority of autonomous RL algorithms require a large number of interactions with the environment. A large number of interactions may be impractical in many real…

Develops methods to simulate rare transitions in molecular systems.

New STH distance finds patterns in event timeseries without resampling.

We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under temporal drifts, ie, both the reward and state transition distributions are allowed to evolve over time, as long as their respective total variations, quantified by suitable metrics, do not exceed certain variation budgets. …

New algorithm reduces regret and constraint violation in adversarial CMDP learning.