Composing Task Knowledge with Modular Successor Feature Approximators
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
Code (1)
Similar Papers 제목 키워드 기반
Successor Feature Representations
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 LearningMeta Reinforcement Learning with Successor Feature Based Context
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+2Non-Linear Rewards For Successor Features
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
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
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)