paper-with-me

홈 › Papers

Learning Successor Features the Simple Way

2024-10-29 · Raymond Chua, Arna Ghosh, Christos Kaplanis, Blake A. Richards, Doina Precup

In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference in non-stationary environments. Successor Features (SFs) offer a potential solution to this challenge. However, canonical techniques for learning SFs from pixel-level observations often lead to representation collapse, wherein representations degenerate and fail to capture meaningful variations in the data. More recent methods for learning SFs can avoid representation collapse, but they often involve complex losses and multiple learning phases, reducing their efficiency. We introduce a novel, simple method for learning SFs directly from pixels. Our approach uses a combination of a Temporal-difference (TD) loss and a reward prediction loss, which together capture the basic mathematical definition of SFs. We show that our approach matches or outperforms existing SF learning techniques in both 2D (Minigrid), 3D (Miniworld) mazes and Mujoco, for both single and continual learning scenarios. As well, our technique is efficient, and can reach higher levels of performance in less time than other approaches. Our work provides a new, streamlined technique for learning SFs directly from pixel observations, with no pretraining required.

📄 PDF Abstract BibTeX arXiv:2410.22133

Code (1)

raymondchua/simple_successor_features 공식 구현 pytorch

Tasks

Continual LearningDeep Reinforcement LearningMuJoCoReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Distributional Successor Features Enable Zero-Shot Policy Optimization

2024-03-10 · Chuning Zhu, Xinqi Wang, Tyler Han, Simon S. Du 외

Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary rewar…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Universal Successor Features for Transfer Reinforcement Learning

2020-01-05 · ICLR 2019 5 · Chen Ma, Dylan R. Ashley, Junfeng Wen, Yoshua Bengio

Transfer in Reinforcement Learning (RL) refers to the idea of applying knowledge gained from previous tasks to solving related tasks. Learning a universal value function (Schaul et al., 2015), which generalizes over goal…

MuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

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)

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

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)