.png){kind=icon}
返回
Phasic parallel-network policy: a deep reinforcement learning framework based on action correlation
.png){kind=icon}
PRE
AI
DOI：10.1007/s00607-024-01329-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Reinforcement learning algorithms show significant variations in performance across different environments. Optimization for reinforcement learning thus becomes the major research task since the instability and unpredictability of the reinforcement learning algorithms have consistently hindered their generalization capabilities. In this study, we address this issue by optimizing the algorithm itself rather than environment-specific optimizations. We start by tackling the uncertainty caused by the mutual influence of original action interferences, aiming to enhance the overall performance. The Phasic Parallel-Network Policy (PPP), which is a deep reinforcement learning framework. It diverges from the traditional policy actor-critic method by grouping the action space based on action correlations. The PPP incorporates parallel network structures and combines network optimization strategies. With the assistance of the value network, the training process is divided into different specific stages, namely the Extra-group Policy Phase and the Inter-group Optimization Phase. PPP breaks through the traditional unit learning structure. The experimental results indicate that it not only optimizes training effectiveness but also reduces training steps, enhances sample efficiency, and significantly improves stability and generalization.
Keyword:
Reinforcement learning
Machine learning
Artificial intelligence
Neural Network
Game AI
期刊
C
IF:
2.8
论文数:
2.3K
被引数:
3.5K
机构
引用论文
分享收藏Robust multi-agent reinforcement learning via Bayesian distributional value estimation.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Applications of asynchronous deep reinforcement learning based on dynamic updating weights基于动态权值更新的异步深度强化学习应用APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏Direct Fibrogenic Effects of Dispersed Single-Walled Carbon Nanotubes on Human Lung Fibroblasts
PREAI
分享收藏An effective asynchronous framework for small scale reinforcement learning problemsAPPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏
查看更多内容