paper-with-me

Papers

Composing Task Knowledge with Modular Successor Feature Approximators

2023-01-28 · Wilka Carvalho, Angelos Filos, Richard L. Lewis, Honglak Lee, Satinder Singh

Recently, the Successor Features and Generalized Policy Improvement (SF&GPI) framework has been proposed as a method for learning, composing, and transferring predictive knowledge and behavior. SF&GPI works by having an agent learn predictive representations (SFs) that can be combined for transfer to new tasks with GPI. However, to be effective this approach requires state features that are useful to predict, and these state-features are typically hand-designed. In this work, we present a novel neural network architecture, "Modular Successor Feature Approximators" (MSFA), where modules both discover what is useful to predict, and learn their own predictive representations. We show that MSFA is able to better generalize compared to baseline architectures for learning SFs and modular architectures

📄 PDF Abstract BibTeX arXiv:2301.12305

Code (1)

facebookresearch/minihack pytorch

Similar Papers 제목 키워드 기반

Successor Feature Representations

2021-10-29 · Chris Reinke, Xavier Alameda-Pineda

Transfer in Reinforcement Learning aims to improve learning performance on target tasks using knowledge from experienced source tasks. Successor Representations (SR) and their extension Successor Features (SF) are promin…

Transfer Learning

Meta Reinforcement Learning with Successor Feature Based Context

2022-07-29 · Xu Han, Feng Wu

Most reinforcement learning (RL) methods only focus on learning a single task from scratch and are not able to use prior knowledge to learn other tasks more effectively. Context-based meta RL techniques are recently prop…

continuous-controlContinuous ControlMeta Reinforcement Learningreinforcement-learning+2

Non-Linear Rewards For Successor Features

2021-01-01 · Norman L Tasfi, Miriam Capretz

Reinforcement Learning algorithms have reached new heights in performance, often overtaking humans on several challenging tasks such as Atari and Go. However, the resulting models learn fragile policies that are unable t…

Second-Order Rewards For Successor Features

2021-09-29 · Norman L Tasfi, Miriam Capretz

Current Reinforcement Learning algorithms have reached new heights in performance. However, such algorithms often require hundreds of millions of samples, often resulting in policies that are unable to transfer between t…

A New Representation of Successor Features for Transfer across Dissimilar Environments

2021-07-18 · Majid Abdolshah, Hung Le, Thommen Karimpanal George, Sunil Gupta 외

Transfer in reinforcement learning is usually achieved through generalisation across tasks. Whilst many studies have investigated transferring knowledge when the reward function changes, they have assumed that the dynami…

Gaussian ProcessesReinforcement Learning (RL)