paper-with-me

Papers

Hierarchical Universal Value Function Approximators

2024-10-11 · Rushiv Arora

There have been key advancements to building universal approximators for multi-goal collections of reinforcement learning value functions -- key elements in estimating long-term returns of states in a parameterized manner. We extend this to hierarchical reinforcement learning, using the options framework, by introducing hierarchical universal value function approximators (H-UVFAs). This allows us to leverage the added benefits of scaling, planning, and generalization expected in temporal abstraction settings. We develop supervised and reinforcement learning methods for learning embeddings of the states, goals, options, and actions in the two hierarchical value functions: $Q(s, g, o; \theta)$ and $Q(s, g, o, a; \theta)$. Finally we demonstrate generalization of the HUVFAs and show they outperform corresponding UVFAs.

📄 PDF Abstract BibTeX arXiv:2410.08997

Code (0)

등록된 구현이 없습니다.

Tasks

Hierarchical Reinforcement Learningreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Deep Neural Networks: A Formulation Via Non-Archimedean Analysis

2024-01-31 · W. A. Zúñiga-Galindo

We introduce a new class of deep neural networks (DNNs) with multilayered tree-like architectures. The architectures are codified using numbers from the ring of integers of non-Archimdean local fields. These rings have a…

Parameterized Convex Universal Approximators for Decision-Making Problems

2022-01-17 · Jinrae Kim, Youdan Kim

Parameterized max-affine (PMA) and parameterized log-sum-exp (PLSE) networks are proposed for general decision-making problems. The proposed approximators generalize existing convex approximators, namely, max-affine (MA)…

Decision Making

Universal Successor Features Approximators

2018-12-18 · ICLR 2019 5 · Diana Borsa, André Barreto, John Quan, Daniel Mankowitz 외

The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of informat…

NavigateReinforcement LearningReinforcement Learning (RL)

Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators

2020-06-20 · NeurIPS 2020 12 · Takeshi Teshima, Isao Ishikawa, Koichi Tojo, Kenta Oono 외

Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. However, their desirable characteristics such as analytic inver…

Image GenerationRepresentation Learning

Universal Function Approximation on Graphs

2020-03-14 · NeurIPS 2020 12 · Rickard Brüel-Gabrielsson

In this work we produce a framework for constructing universal function approximators on graph isomorphism classes. We prove how this framework comes with a collection of theoretically desirable properties and enables no…

Dependency ParsingGraph ClassificationGraph Learning