Results 21 to 30 of about 6,292,535 (287)
Coordinated Proximal Policy Optimization
CoRR, 2021 We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. The key idea lies in the coordinated adaptation of step size during the policy update process among multiple agents.
Zifan Wu +5 more
openaire +3 more sources
An AGC Dynamic Optimization Method Based on Proximal Policy Optimization
Frontiers in Energy Research, 2022 The increasing penetration of renewable energy introduces more uncertainties and creates more fluctuations in power systems than ever before, which brings great challenges for automatic generation control (AGC).
Zhao Liu +4 more
doaj +1 more source
Generalized proximal policy optimization with sample reuse [PDF]
, 2021 In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while off-policy methods make
Cassandras, Christos G. +2 more
core +1 more source
Riemannian Proximal Policy Optimization
Computer and Information Science, 2020 In this paper, we propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy functions in MDP, we employ Gaussian mixture model (GMM) and formulate it as a non-convex optimization problem in the Riemannian space of positive semidefinite matrices.
Shijun Wang +6 more
openaire +4 more sources
Decaying Clipping Range in Proximal Policy Optimization [PDF]
2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI), 2021 Proximal Policy Optimization (PPO) is among the most widely used algorithms in reinforcement learning, which achieves state-of-the-art performance in many challenging problems. The keys to its success are the reliable policy updates through the clipping mechanism and the multiple epochs of minibatch updates.
Mónika Farsang, Luca Szegletes
openaire +3 more sources
Optimistic Proximal Policy Optimization
CoRR, 2019 Exploration in RL (workshop @ ICML2019)
Takahisa Imagawa +2 more
openaire +2 more sources
Improving traffic signal control operations using proximal policy optimization
IET Intelligent Transport Systems, 2023 Existing traffic signal control systems present many limitations including fixed signal timing schemes, insufficient efficiency and flexibility, and difficulty in adapting to the changing traffic flows.
Liben Huang, Xiaohui Qu
doaj +1 more source
Proximal Policy Optimization Algorithms
CoRR, 2017 We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent. Whereas standard policy gradient methods perform one gradient update per data sample, we propose a novel ...
John Schulman +4 more
openaire +2 more sources
Replication Data for: eSLP optimization algorithm
, 2023 m-files implementing the eSLP optimization algorithm for the three simulations (3.1. - 3.3.) described in the associated paper. File README.txt contains analytical directions regarding requirements, how to verify the results and videos generated by the ...
Optimization, eSLP
core +1 more source
Proximal Policy Optimization Smoothed Algorithm
CoRR, 2020 13 pages, 6 figures, 3 tables ...
Wangshu Zhu, Andre Rosendo
openaire +3 more sources