paper-with-me

홈 › Papers

Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control

2017-08-10 · Riashat Islam, Peter Henderson, Maziar Gomrokchi, Doina Precup

Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic policy gradients and trust region policy optimization. As such, it is important to present and use consistent baselines experiments. However, this can be difficult due to general variance in the algorithms, hyper-parameter tuning, and environment stochasticity. We investigate and discuss: the significance of hyper-parameters in policy gradients for continuous control, general variance in the algorithms, and reproducibility of reported results. We provide guidelines on reporting novel results as comparisons against baseline methods such that future researchers can make informed decisions when investigating novel methods.

📄 PDF Abstract BibTeX arXiv:1708.04133

Code (1)

Breakend/ReproducibilityInContinuousPolicyGradientMethods 공식 구현 tf

Tasks

continuous-controlContinuous ControlDeep Reinforcement LearningPolicy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Benchmarking Deep Reinforcement Learning for Continuous Control

2016-04-22 · Yan Duan, Xi Chen, Rein Houthooft, John Schulman 외

Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari g…

Action Triplet RecognitionAtari GamesBenchmarkingcontinuous-control+5

ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation

2020-08-18 · Fei Xia, Chengshu Li, Roberto Martín-Martín, Or Litany 외

Many Reinforcement Learning (RL) approaches use joint control signals (positions, velocities, torques) as action space for continuous control tasks. We propose to lift the action space to a higher level in the form of su…

continuous-controlContinuous ControlHierarchical Reinforcement LearningMotion Generation+3

ModelPredictiveControl.jl: advanced process control made easy in Julia

2024-11-14 · Francis Gagnon, Alex Thivierge, André Desbiens, Fredrik Bagge Carlson

Proprietary closed-source software is still the norm in advanced process control. Transparency and reproducibility are key aspects of scientific research. Free and open-source toolkit can contribute to the development, s…

Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control

2020-10-19 · Guangzhi Tang, Neelesh Kumar, Raymond Yoo, Konstantinos P. Michmizos

The energy-efficient control of mobile robots is crucial as the complexity of their real-world applications increasingly involves high-dimensional observation and action spaces, which cannot be offset by limited on-board…

continuous-controlContinuous ControlDeep Reinforcement LearningOpenAI Gym+2

Stabilizing Off-Policy Reinforcement Learning with Conservative Policy Gradients

2019-09-25 · Chen Tessler, Nadav Merlis, Shie Mannor

In recent years, advances in deep learning have enabled the application of reinforcement learning algorithms in complex domains. However, they lack the theoretical guarantees which are present in the tabular setting and …

Deep Reinforcement LearningMuJoCoreinforcement-learningReinforcement Learning+1