paper-with-me

홈 › Papers

Exploiting the Sign of the Advantage Function to Learn Deterministic Policies in Continuous Domains

2019-06-10 · Matthieu Zimmer, Paul Weng

In the context of learning deterministic policies in continuous domains, we revisit an approach, which was first proposed in Continuous Actor Critic Learning Automaton (CACLA) and later extended in Neural Fitted Actor Critic (NFAC). This approach is based on a policy update different from that of deterministic policy gradient (DPG). Previous work has observed its excellent performance empirically, but a theoretical justification is lacking. To fill this gap, we provide a theoretical explanation to motivate this unorthodox policy update by relating it to another update and making explicit the objective function of the latter. We furthermore discuss in depth the properties of these updates to get a deeper understanding of the overall approach. In addition, we extend it and propose a new trust region algorithm, Penalized NFAC (PeNFAC). Finally, we experimentally demonstrate in several classic control problems that it surpasses the state-of-the-art algorithms to learn deterministic policies.

📄 PDF Abstract BibTeX arXiv:1906.04556

Code (1)

matthieu637/ddrl 공식 구현 tf

Similar Papers 제목 키워드 기반

Zeroth-order Deterministic Policy Gradient

2020-06-12 · Harshat Kumar, Dionysios S. Kalogerias, George J. Pappas, Alejandro Ribeiro

Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling complex dynamic problems involving Marko…

Deep Reinforcement Learning with Discrete Normalized Advantage Functions for Resource Management in Network Slicing

2019-06-10 · Chen Qi, Yuxiu Hua, Rongpeng Li, Zhifeng Zhao 외

Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep $\mathcal{Q}$-learning, DQL) is assumed to be an appropriate algorithm …

Deep Reinforcement LearningManagementQ-LearningReinforcement Learning+2

The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning

2020-06-23 · Lingheng Meng, Rob Gorbet, Dana Kulić

Multi-step (also called n-step) methods in reinforcement learning (RL) have been shown to be more efficient than the 1-step method due to faster propagation of the reward signal, both theoretically and empirically, in ta…

Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Exploiting Functional Dependencies in Qualitative Probabilistic Reasoning

2013-03-27 · Michael P. Wellman

Functional dependencies restrict the potential interactions among variables connected in a probabilistic network. This restriction can be exploited in qualitative probabilistic reasoning by introducing deterministic vari…

Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks

2023-05-25 · Gehua Ma, Rui Yan, Huajin Tang

$\textbf{Formal version available at}$ https://cell.com/patterns/fulltext/S2666-3899(23)00200-3 Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pill…