arXiv research

New model-based methods adapt pre-trained policies to unseen environments efficiently.

UAED discovers adaptive environments for robust learning.

Paper tackles noise-robust domain adaptation in noisy environments.

Adaptive linear bandit algorithm with best-of-three-worlds regret bounds.

CARL safely adapts RL agents for safety-critical tasks.

Self-supervised policy adapts after deployment without rewards.

BAM integrates new data while selectively remembering past observations.

AdaRL adapts quickly to new environments with minimal data.

Selective reinitialization improves adaptability of neural bandits in dynamic environments.

New algorithms reduce dynamic regret in non-stationary RL environments.

New method improves RL/IL agents' adaptability to unseen environments.

New algorithm for nonstationary multi-armed bandits with optimal performance.

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…

We propose algorithms for online principal component analysis (PCA) and variance minimization for adaptive settings. Previous literature has focused on upper bounding the static adversarial regret, whose comparator is the optimal fixed action in hindsight. However, static regret is not an appropriate metric when the un…

OSAMD adapts online to changing distributions with limited labels.

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…

Online convex optimization is a sequential prediction framework with the goal to track and adapt to the environment through evaluating proper convex loss functions. We study efficient particle filtering methods from the perspective of such a framework. We formulate an efficient particle filtering methods for the non-st…

New algorithms adaptively calibrate predictions in non-stationary environments, matching optimal rates.

Adaptive online learning algorithm improves history forgetting in nonstationary environments.

FADE adapts machine learning models to evolving data efficiently.

To deal with changing environments, a new performance measure -- adaptive regret, defined as the maximum static regret over any interval, was proposed in online learning. Under the setting of online convex optimization, several algorithms have been successfully developed to minimize the adaptive regret. However, existi…

This paper tackles continuous domain adaptation with a new approach.

Proposes a method to adapt models in nonstationary environments using ℓ1 regularization.

A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed "meta" algorithms that convert any online learning algorithm to one that is adaptive to changing environments, where the adaptivity is analyzed in a quantity called the strongly-ad…

A model is developed to study the effectiveness of innovation and its impact on structure creation and structure change on agent-based societies. The abstract model that is developed is easily adapted to any particular field. In any interacting environment, the agents receive something from the environment (the other a…

We propose a novel approach to address one aspect of the non-stationarity problem in multi-agent reinforcement learning (RL), where the other agents may alter their policies due to environment changes during execution. This violates the Markov assumption that governs most single-agent RL methods and is one of the key c…

The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward functions for environments with the same (or similar) dynamical models. We propose to l…

Survey of RL algorithms for dynamic environments.

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…

This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of learning temporal relationships and translation invariant representations, is u…

Foundation models struggle with multi-turn exploration but can learn through regular summaries.

The study explores how agents learn and adapt preferences in dynamic environments.

Efficiently adapting to new environments and changes in dynamics is critical for agents to successfully operate in the real world. Reinforcement learning (RL) based approaches typically rely on external reward feedback for adaptation. However, in many scenarios this reward signal might not be readily available for the …

CoDA adapts dynamics models to new physical systems by conditioning on context.

The paper proposes a method to adapt machine learning models to changing conditions.

New method learns adaptive exploration strategies for dynamic tasks.

Learning in a non-stationary environment is an inevitable problem when applying machine learning algorithm to real world environment. Learning new tasks without forgetting the previous knowledge is a challenge issue in machine learning. We propose a Kalman Filter based modifier to maintain the performance of Neural Net…

Meta-learning improves drone trajectory design for dynamic wireless networks.

A new method helps deep learning systems adapt to changing conditions.

Adaptive Stress Testing detects financial fraud by simulating potential failures.

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…

A new buffer system improves continual learning in RL agents by adapting to changing environments.

Offline RL policies should adapt to unknown aspects of the environment.

Work maximization guides machine learning models in adaptive systems.

Study improves self-driving safety in dynamic environments.

How do organisms recognize their environment by acquiring knowledge about the world, and what actions do they take based on this knowledge? This article examines hypotheses about organisms' adaptation to the environment from machine learning, information-theoretic, and thermodynamic perspectives. We start with construc…

Machine learning employs dynamical algorithms that mimic the human capacity to learn, where the reinforcement learning ones are among the most similar to humans in this respect. On the other hand, adaptability is an essential aspect to perform any task efficiently in a changing environment, and it is fundamental for ma…

This research introduces an autonomous robot navigation method using reinforcement learning.