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.
LEADS improves model generalization across different environments.
New algorithms reduce dynamic regret in non-stationary RL environments.
Proposes a method to improve few-shot transfer in off-dynamics RL.
Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-s…
Universal online optimization for dynamic environments using uniclass prediction.
While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is often challenging and requires substantial interaction with the environment. A wide variety of domains have dynamics that share common foundations like the laws of clas…
New method improves RL/IL agents' adaptability to unseen environments.
HySRL improves RL sample efficiency with shifted-dynamics data.
We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obst…
Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based approaches lead to `compounding errors' when the model is unrolled step by step. Essentia…
New model predicts dynamic volatility in uncertain financial markets.
New pricing algorithm learns demand curves and optimizes prices in dynamic markets.
New algorithms reduce dynamic regret for convex and smooth functions in non-stationary environments.
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…
HRM-Agent learns to navigate dynamic mazes using reinforcement learning.
This work uses reinforcement learning to optimize task scheduling and execution in a dynamic multi-agent warehouse environment.
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 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…
Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of the environment for motion prediction. This modularity explicitly allows for unsupervised adaptation of trajectory prediction models to unseen…
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…
Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.
We describe theoretical bounds and a practical algorithm for teaching a model by demonstration in a sequential decision making environment. Unlike previous efforts that have optimized learners that watch a teacher demonstrate a static policy, we focus on the teacher as a decision maker who can dynamically choose differ…
Meta-learning improves drone trajectory design for dynamic wireless networks.
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especiall…
Bayesian Federated Learning improves model reliability in dynamic environments.
Survey of RL algorithms for dynamic environments.
CoDA adapts dynamics models to new physical systems by conditioning on context.
This work develops agents to learn generalizable policies for dynamic network environments.
Selective reinitialization improves adaptability of neural bandits in dynamic environments.
In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an dynamic regret, where is the number of iterations and is the path-le…
Autonomous lane changing is a critical feature for advanced autonomous driving systems, that involves several challenges such as uncertainty in other driver's behaviors and the trade-off between safety and agility. In this work, we develop a novel simulation environment that emulates these challenges and train a deep r…
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 …
CARL controls a quadruped to move naturally in complex environments.
DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.
This paper presents a methodology that aims at the incremental representation of areas inside environments in terms of attractive forces. It is proposed a parametric representation of velocity fields ruling the dynamics of moving agents. It is assumed that attractive spots in the environment are responsible for modifyi…
Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe in terms of symmetry preserving transformations. Inspired by this formalism, we propose a framew…
New method learns adaptive exploration strategies for dynamic tasks.
Proposes DLGPD model to learn dynamics from images for planning.
Inverse reinforcement learning has proved its ability to explain state-action trajectories of expert agents by recovering their underlying reward functions in increasingly challenging environments. Recent advances in adversarial learning have allowed extending inverse RL to applications with non-stationary environment …
The study questions the necessity of accurate models in MBRL.
We consider online forecasting problems for non-convex machine learning models. Forecasting introduces several challenges such as (i) frequent updates are necessary to deal with concept drift issues since the dynamics of the environment change over time, and (ii) the state of the art models are non-convex models. We ad…
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.
Proposes a method to learn policies from offline data with reduced bias.
Optimally explores dynamical systems with varying properties using context inference.
In many application areas---lending, education, and online recommenders, for example---fairness and equity concerns emerge when a machine learning system interacts with a dynamically changing environment to produce both immediate and long-term effects for individuals and demographic groups. We discuss causal directed a…
Model-based reinforcement learning algorithms make decisions by building and utilizing a model of the environment. However, none of the existing algorithms attempts to infer the dynamics of any state-action pair from known state-action pairs before meeting it for sufficient times. We propose a new model-based method ca…
Predicting movement of objects while the action of learning agent interacts with the dynamics of the scene still remains a key challenge in robotics. We propose a multi-layer Long Short Term Memory (LSTM) autoendocer network that predicts future frames for a robot navigating in a dynamic environment with moving obstacl…
The Surprise index assesses autonomous systems' competency in uncertain environments.