paper-with-me

홈 › Papers

Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling

2019-10-05 · ICML 2020 1 · Che Wang, Yanqiu Wu, Quan Vuong, Keith Ross

We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft Actor-Critic (SAC), which employs entropy maximization, currently provides state-of-the-art performance. We first demonstrate that the entropy term in SAC addresses action saturation due to the bounded nature of the action spaces, with this insight, we propose a streamlined algorithm with a simple normalization scheme or with inverted gradients. We show that both approaches can match SAC's sample efficiency performance without the need of entropy maximization, we then propose a simple non-uniform sampling method for selecting transitions from the replay buffer during training. Extensive experimental results demonstrate that our proposed sampling scheme leads to state of the art sample efficiency on challenging continuous control tasks. We combine all of our findings into one simple algorithm, which we call Streamlined Off Policy with Emphasizing Recent Experience, for which we provide robust public-domain code.

📄 PDF Abstract BibTeX arXiv:1910.02208

Code (3)

AutumnWu/Streamlined-Off-Policy-Learning 공식 구현 tf
Fable67/Streamlined-Off-Policy-Learning pytorch
angelolovatto/raylab pytorch

Tasks

continuous-controlContinuous Control

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Adam 설명 없음
Soft Actor Critic Soft Actor Critic, or SAC, is an off-policy actor-critic deep RL algorithm based on the maximum entropy reinforcement learning framework. In this framework, the actor aims…

Similar Papers 제목 키워드 기반

DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning

2020-06-26 · Rasool Fakoor, Pratik Chaudhari, Alexander J. Smola

This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works r…

continuous-controlContinuous ControlMuJoCoreinforcement-learning+1

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

2024-10-13 · Hojoon Lee, Dongyoon Hwang, Donghu Kim, Hyunseung Kim 외

Recent advances in CV and NLP have been largely driven by scaling up the number of network parameters, despite traditional theories suggesting that larger networks are prone to overfitting. These large networks avoid ove…

Computational EfficiencyDeep Reinforcement Learning

Striving for Simplicity in Off-Policy Deep Reinforcement Learning

2019-09-25 · Rishabh Agarwal, Dale Schuurmans, Mohammad Norouzi

This paper advocates the use of offline (batch) reinforcement learning (RL) to help (1) isolate the contributions of exploitation vs. exploration in off-policy deep RL, (2) improve reproducibility of deep RL research, an…

Atari GamesDeep Reinforcement LearningOffline RLQ-Learning+3

Learning Nonparametric High-Dimensional Generative Models: The Empirical-Beta-Copula Autoencoder

2023-09-18 · Maximilian Coblenz, Oliver Grothe, Fabian Kächele

By sampling from the latent space of an autoencoder and decoding the latent space samples to the original data space, any autoencoder can simply be turned into a generative model. For this to work, it is necessary to mod…

Batch Normalization with Enhanced Linear Transformation

2020-11-28 · Yuhui Xu, Lingxi Xie, Cihang Xie, Jieru Mei 외

Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions. In this paper, we demonst…