paper-with-me

Papers

Bilinear value networks

2022-04-28 · Zhang-Wei Hong, Ge Yang, Pulkit Agrawal

The dominant framework for off-policy multi-goal reinforcement learning involves estimating goal conditioned Q-value function. When learning to achieve multiple goals, data efficiency is intimately connected with the generalization of the Q-function to new goals. The de-facto paradigm is to approximate Q(s, a, g) using monolithic neural networks. To improve the generalization of the Q-function, we propose a bilinear decomposition that represents the Q-value via a low-rank approximation in the form of a dot product between two vector fields. The first vector field, f(s, a), captures the environment's local dynamics at the state s; whereas the second component, {\phi}(s, g), captures the global relationship between the current state and the goal. We show that our bilinear decomposition scheme substantially improves data efficiency, and has superior transfer to out-of-distribution goals compared to prior methods. Empirical evidence is provided on the simulated Fetch robot task-suite and dexterous manipulation with a Shadow hand.

📄 PDF Abstract BibTeX arXiv:2204.13695

Code (1)

improbable-ai/bvn 공식 구현 pytorch

Tasks

Multi-Goal Reinforcement Learning

Similar Papers 제목 키워드 기반

Robust Value Function Approximation Using Bilinear Programming

2009-12-01 · NeurIPS 2009 12 · Marek Petrik, Shlomo Zilberstein

Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds. We propose approximate bilinear programming, a new formulation of value fu…

Recurrent Bilinear Optimization for Binary Neural Networks

2022-09-04 · Sheng Xu, Yanjing Li, Tiancheng Wang, Teli Ma 외

Binary Neural Networks (BNNs) show great promise for real-world embedded devices. As one of the critical steps to achieve a powerful BNN, the scale factor calculation plays an essential role in reducing the performance g…

object-detectionObject Detection

Backpropagation with N-D Vector-Valued Neurons Using Arbitrary Bilinear Products

2018-05-24 · Zhe-Cheng Fan, Tak-Shing T. Chan, Yi-Hsuan Yang, Jyh-Shing R. Jang

Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not…

DenoisingImage Denoising

A framework for fitting quadratic-bilinear systems with applications to models of electrical circuits

2021-12-02 · Dimitrios S. Karachalios, Ion Victor Gosea, Athanasios C. Antoulas

In this contribution, we propose a data-driven procedure to fit quadratic-bilinear surrogate models from data. Although the dynamics characterizing the original model are strongly nonlinear, we rely on lifting techniques…

Bilinear Convolution Decomposition for Causal RL Interpretability

2024-12-01 · Narmeen Oozeer, Sinem Erisken, Alice Rigg

Efforts to interpret reinforcement learning (RL) models often rely on high-level techniques such as attribution or probing, which provide only correlational insights and coarse causal control. This work proposes replacin…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)