Results 261 to 270 of about 6,292,535 (287)
Some of the next articles are maybe not open access.
Proximal Policy Optimization With Policy Feedback
IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022Proximal policy optimization (PPO) is a deep reinforcement learning algorithm based on the actor-critic (AC) architecture. In the classic AC architecture, the Critic (value) network is used to estimate the value function while the Actor (policy) network optimizes the policy according to the estimated value function.
Philip N L Chen +2 more
exaly +2 more sources
Anti-Martingale Proximal Policy Optimization
IEEE Transactions on Cybernetics, 2023Since the sample data after one exploration process can only be used to update network parameters once in on-policy deep reinforcement learning (DRL), a high sample efficiency is necessary to accelerate the training process of on-policy DRL. In the proposed method, a submartingale criterion is proposed on the basis of the equivalence relationship ...
Kun Yu, Xuesong Wang, Yuhu Cheng
exaly +3 more sources
Authentic Boundary Proximal Policy Optimization
IEEE Transactions on Cybernetics, 2022In recent years, the proximal policy optimization (PPO) algorithm has received considerable attention because of its excellent performance in many challenging tasks. However, there is still a large space for theoretical explanation of the mechanism of PPO's horizontal clipping operation, which is a key means to improve the performance of PPO.
Xuesong Wang, Yuhu Cheng, Longyang Huang
exaly +4 more sources
Improving proximal policy optimization with alpha divergence
Neurocomputing, 2023Junyu Xuan, Guangquan Zhang, Haotian Xu
exaly +2 more sources
Candidate ratio guided proximal policy optimization
Engineering Applications of Artificial IntelligenceXiaoyang Tan
exaly +3 more sources
Preferential Proximal Policy Optimization
2023 International Conference on Machine Learning and Applications (ICMLA), 2023Tamilselvan Balasuntharam +2 more
openaire +1 more source
Proximal Policy Optimization in StarCraft
Deep reinforcement learning is an area of research that has blossomed tremendously in recent years and has shown remarkable potential in computer games. Real-time strategy game has become an important field of artificial intelligence in game for several years.openaire +2 more sources
Proximal policy optimization via enhanced exploration efficiency
Information Sciences, 2022Shuai Lu, Zhenghao Zhang, Shuai Han
exaly