English
Related papers

Related papers: Generation of Geodesics with Actor-Critic Reinforc…

200 papers

In recent decades, advancements in motion learning have enabled robots to acquire new skills and adapt to unseen conditions in both structured and unstructured environments. In practice, motion learning methods capture relevant patterns and…

Robotics · Computer Science 2023-08-21 Hadi Beik-Mohammadi , Søren Hauberg , Georgios Arvanitidis , Gerhard Neumann , Leonel Rozo

We develop a new method for visualizing and refining the invariances of learned representations. Specifically, we test for a general form of invariance, linearization, in which the action of a transformation is confined to a low-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Olivier J. Hénaff , Eero P. Simoncelli

Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only…

Machine Learning · Statistics 2018-02-23 Voot Tangkaratt , Abbas Abdolmaleki , Masashi Sugiyama

The length of the geodesic between two data points along a Riemannian manifold, induced by a deep generative model, yields a principled measure of similarity. Current approaches are limited to low-dimensional latent spaces, due to the…

Substantial advancements to model-based reinforcement learning algorithms have been impeded by the model-bias induced by the collected data, which generally hurts performance. Meanwhile, their inherent sample efficiency warrants utility for…

In this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input. Our neural architecture is composed of a critic and an actor network. Both networks receive…

Machine Learning · Computer Science 2019-02-19 Muhammad Burhan Hafez , Cornelius Weber , Matthias Kerzel , Stefan Wermter

We propose the Mean-Field Actor-Critic (MFAC) flow, a continuous-time learning dynamics for solving mean-field games (MFGs), combining techniques from reinforcement learning and optimal transport. The MFAC framework jointly evolves the…

Optimization and Control · Mathematics 2025-10-27 Mo Zhou , Haosheng Zhou , Ruimeng Hu

For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly. This demands learning models that capture relevant motion patterns, while…

Robotics · Computer Science 2021-07-02 Hadi Beik-Mohammadi , Søren Hauberg , Georgios Arvanitidis , Gerhard Neumann , Leonel Rozo

Manifolds discovered by machine learning models provide a compact representation of the underlying data. Geodesics on these manifolds define locally length-minimising curves and provide a notion of distance, which are key for reduced-order…

Machine Learning · Computer Science 2023-05-25 Daniel Kelshaw , Luca Magri

In this paper, we propose the first method to modify the prosodic features of a given speech signal using actor-critic reinforcement learning strategy. Our approach uses a Bayesian framework to identify contiguous segments of importance…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-06 Ravi Shankar , Archana Venkataraman

In this article, we will formulate a mathematical framework that allows us to treat character animations as points on infinite dimensional Hilbert manifolds. Constructing geodesic paths between animations on those manifolds allows us to…

Differential Geometry · Mathematics 2014-05-19 Markus Eslitzbichler

In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations. In this manuscript we focus on predictions expressed as General Value Functions:…

Machine Learning · Computer Science 2021-11-23 Alex Kearney , Anna Koop , Johannes Günther , Patrick M. Pilarski

Actor-critic (AC) methods are widely used in reinforcement learning (RL) and benefit from the flexibility of using any policy gradient method as the actor and value-based method as the critic. The critic is usually trained by minimizing the…

Machine Learning · Computer Science 2023-11-01 Sharan Vaswani , Amirreza Kazemi , Reza Babanezhad , Nicolas Le Roux

Geodesic paths and distances are among the most popular intrinsic properties of 3D surfaces. Traditionally, geodesic paths on discrete polygon surfaces were computed using shortest path algorithms, such as Dijkstra. However, such algorithms…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Rolandos Alexandros Potamias , Alexandros Neofytou , Kyriaki-Margarita Bintsi , Stefanos Zafeiriou

Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning. In this paper, we show how to make more effective use of the…

Machine Learning · Computer Science 2020-05-19 Ignasi Clavera , Violet Fu , Pieter Abbeel

This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on…

Machine Learning · Computer Science 2015-03-20 Thomas Degris , Martha White , Richard S. Sutton

In this paper, we devise three actor-critic algorithms with decentralized training for multi-agent reinforcement learning in cooperative, adversarial, and mixed settings with continuous action spaces. To this goal, we adapt the MADDPG…

Machine Learning · Computer Science 2025-03-11 Diego Bolliger , Lorenz Zauter , Robert Ziegler

One of the most challenging aspects of real-world reinforcement learning (RL) is the multitude of unpredictable and ever-changing distractions that could divert an agent from what was tasked to do in its training environment. While an agent…

Machine Learning · Computer Science 2020-11-17 Cristian Bodnar , Karol Hausman , Gabriel Dulac-Arnold , Rico Jonschkowski

We study policy gradient for mean-field control in continuous time in a reinforcement learning setting. By considering randomised policies with entropy regularisation, we derive a gradient expectation representation of the value function,…

Machine Learning · Statistics 2023-03-14 Noufel Frikha , Maximilien Germain , Mathieu Laurière , Huyên Pham , Xuanye Song

In recent years, deep learning has made remarkable strides, surpassing human capabilities in tasks like strategy games, and it has found applications in complex domains, including protein folding. In the realm of quantum chemistry, machine…

Chemical Physics · Physics 2024-01-09 Rhyan Barrett , Julia Westermayr
‹ Prev 1 2 3 10 Next ›