paper-with-me

홈 › Papers

Q-Value Weighted Regression: Reinforcement Learning with Limited Data

2021-02-12 · Piotr Kozakowski, Łukasz Kaiser, Henryk Michalewski, Afroz Mohiuddin, Katarzyna Kańska

Sample efficiency and performance in the offline setting have emerged as significant challenges of deep reinforcement learning. We introduce Q-Value Weighted Regression (QWR), a simple RL algorithm that excels in these aspects. QWR is an extension of Advantage Weighted Regression (AWR), an off-policy actor-critic algorithm that performs very well on continuous control tasks, also in the offline setting, but has low sample efficiency and struggles with high-dimensional observation spaces. We perform an analysis of AWR that explains its shortcomings and use these insights to motivate QWR. We show experimentally that QWR matches the state-of-the-art algorithms both on tasks with continuous and discrete actions. In particular, QWR yields results on par with SAC on the MuJoCo suite and - with the same set of hyperparameters - yields results on par with a highly tuned Rainbow implementation on a set of Atari games. We also verify that QWR performs well in the offline RL setting.

📄 PDF Abstract BibTeX arXiv:2102.06782

Code (1)

vub-ai-lab/qwr pytorch

Tasks

Atari Gamescontinuous-controlContinuous ControlDeep Reinforcement LearningMuJoCoOffline RLregressionreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Dilated Convolution 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Average Pooling 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
SAC 설명 없음

Similar Papers 제목 키워드 기반

Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice

2023-05-22 · Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang, Nino Vieillard 외

Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performing practical RL algorithms. However, des…

regressionReinforcement Learning (RL)

Reward-Weighted Regression Converges to a Global Optimum

2021-07-19 · Miroslav Štrupl, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava 외

Reward-Weighted Regression (RWR) belongs to a family of widely known iterative Reinforcement Learning algorithms based on the Expectation-Maximization framework. In this family, learning at each iteration consists of sam…

regressionReinforcement Learning (RL)

Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

2019-10-01 · Xue Bin Peng, Aviral Kumar, Grace Zhang, Sergey Levine

In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent max…

continuous-controlContinuous ControlOpenAI Gymregression+3

Advantage Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

2019-09-25 · Xue Bin Peng, Aviral Kumar, Grace Zhang, Sergey Levine

In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent max…

continuous-controlContinuous ControlOpenAI Gymregression+3

Wrapped Gaussian Process Regression on Riemannian Manifolds

2018-06-01 · CVPR 2018 6 · Anton Mallasto, Aasa Feragen

Gaussian process (GP) regression is a powerful tool in non-parametric regression providing uncertainty estimates. However, it is limited to data in vector spaces. In fields such as shape analysis and diffusion tensor ima…

Gaussian Processesregression