A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New algorithm learns safe policies in unknown environments.
CoCoRL learns safe constraints from demonstrations with unknown rewards.
New algorithm for reinforcement learning in uncertain environments with unknown thresholds.
Neural Laplace Control tackles offline RL for continuous-time delayed systems with irregular observations.
Kernel-based methods exhibit well-documented performance in various nonlinear learning tasks. Most of them rely on a preselected kernel, whose prudent choice presumes task-specific prior information. Especially when the latter is not available, multi-kernel learning has gained popularity thanks to its flexibility in ch…
To maximize its success, an AGI typically needs to explore its initially unknown world. Is there an optimal way of doing so? Here we derive an affirmative answer for a broad class of environments.
Method identifies unknown intervention targets in structural causal models from diverse data.
Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions its actions not only on the environment state but on the agent's uncertainty about the environment. Computing a Bayes-optimal policy is how…
New algorithm reduces dynamic regret for MDPs with unknown transition and adversarial rewards.
In many important machine learning applications, the training distribution used to learn a probabilistic classifier differs from the testing distribution on which the classifier will be used to make predictions. Traditional methods correct the distribution shift by reweighting the training data with the ratio of the de…
This paper tackles CRL for multi-node interventions, achieving identifiability guarantees.
We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents are trying to solve. To do so, we extend previous probabilistic approaches for in…
We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents are trying to solve. To do so, we extend previous probabilistic approaches for in…
The paper shows how to learn causal representations with few environments and finite samples.
New RL approach learns dynamic VCG mechanisms in unknown MDP environments.
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but requ…
UAV uses RL to navigate, map, and detect targets in unknown environments.
Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself a…
In this paper we address speaker-independent multichannel speech enhancement in unknown noisy environments. Our work is based on a well-established multichannel local Gaussian modeling framework. We propose to use a neural network for modeling the speech spectro-temporal content. The parameters of this supervised model…
Deep learning agent improves pedestrian navigation in urban environments.
Algorithm learns from offline data to improve performance in target environment.
Improved RL algorithm stabilizes unknown linear systems with polynomial regret.
Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics. Partially observable Markov decision processes (POMDPs) allow for the modeling of both. Unfortunately, they do not p…
This research generates synthetic data streams for handling concept drifts and novel classes.
GIM learns by analogy to improve reinforcement learning efficiency.
FAIR-NN finds invariant variables for causal inference across diverse environments.
Greedy policy maximizes information in unknown linear systems.
New algorithms adaptively calibrate predictions in non-stationary environments, matching optimal rates.
Iterative method learns unknown constraints for MPC control.
AI agent learns to handle unknown unknown states in reinforcement learning.
This paper proposes a formal approach to online learning and planning for agents operating in a priori unknown, time-varying environments. The proposed method computes the maximally likely model of the environment, given the observations about the environment made by an agent earlier in the system run and assuming know…
Bayesian nonparametric models improve tracking in cluttered environments.
In classical reinforcement learning, when exploring an environment, agents accept arbitrary short term loss for long term gain. This is infeasible for safety critical applications, such as robotics, where even a single unsafe action may cause system failure. In this paper, we address the problem of safely exploring fin…
Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment. These methods are sample efficient and facilitate learning in the real world but fail to generalize to subtle variations in the underlying dynamics, e.g., due to differences in mass, friction, or actuators a…
Safe learning in uncertain systems with state measurements and optimization.
Computer simulation provides an automatic and safe way for training robotic control policies to achieve complex tasks such as locomotion. However, a policy trained in simulation usually does not transfer directly to the real hardware due to the differences between the two environments. Transfer learning using domain ra…
New algorithms reduce dynamic regret in non-stationary RL environments.
Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement. However, such algorithms usually assume a stationary reward distribution, which hardly holds in practice as users' …
In this paper we target the problem of transferring policies across multiple environments with different dynamics parameters and motor noise variations, by introducing a framework that decouples the processes of policy learning and system identification. Efficiently transferring learned policies to an unknown environme…
The paper proposes a method for distribution-free prediction sets that adapt to unknown temporal changes.
Adversarial RL recovers agent rewards from financial market data simulations.
A new estimator for evaluating policies in unknown environments.
A new buffer system improves continual learning in RL agents by adapting to changing environments.
Optimistic Thompson Sampling reduces regret in unknown multi-player games.
We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environments. To do so, we study how a teacher algorithm can learn to generate a learning curriculum, whereby it sequentially samples parameters contr…
The widespread mobile devices facilitated the emergence of many new applications and services. Among them are location-based services (LBS) that provide services based on user's location. Several techniques have been presented to enable LBS even in indoor environments where Global Positioning System (GPS) has low local…
ARTEO algorithm optimizes safety-critical systems with uncertainty.
CARL safely adapts RL agents for safety-critical tasks.