Batch A3C reinforcement learning method for agent exploring 3D maze

A technology of reinforcement learning and intelligent agents, applied in the direction of neural learning methods, neural architecture, biological neural network models, etc., can solve problems such as inconsistency and RL powerlessness

Active Publication Date: 2018-12-21
BEIJING UNIV OF TECH
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the continuous and complex environment of the reinforcement learning method, the state of the environment may be different every moment, and the bottleneck of the reinforcement learning theory will be revealed.
In the face of high-dimensional, dynamic programming problems with huge state sets, pure RL will appear powerless

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Batch A3C reinforcement learning method for agent exploring 3D maze
  • Batch A3C reinforcement learning method for agent exploring 3D maze

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to further illustrate the purpose, technical solution and features of the present invention, the present invention will be further described below in conjunction with examples of implementing the method and with reference to the accompanying drawings. The invention adopts the batch-based A3C deep reinforcement learning method to realize the agent to explore the 3D maze. Use CNN-MLP to extract the low-dimensional feature vec of the agent's state, and then use LSTM+MLP to respectively predict the prediction of the agent's action distribution based on the current state, and the state value of the current state. This state value approximates the reconstructed action value function . The improvement of the present invention can be summarized in the following two aspects: 1) only one set of neural network parameters is needed, and the deep reinforcement learning based on the A3C algorithm can be completed with the help of experience pool and process technology to com...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a batch A3C reinforcement learning method for an agent to explore a 3D maze. In order to achieve the goal of relatively short training time and small memory loss, the inventionuses a batch-based reinforcement learning method to train a neural network. The neural network is divided into two parts. The first part mainly consists of several convolution layers and MLP, and thelow-dimensional representation of the original screen pixels is obtained. The second part is an LSTM (Long-Short-Term Memory) model. The input of the LSTM is the output of the MLP of the first part,and the cell output of the last time step of the LSTM is circumscribed with two MLPs, which are respectively used to predict the probability distribution of the action a in the current state and the prediction of the state value v in the current state. Combining the efficient reinforcement learning algorithm and depth learning method, the agent can explore 3D maze independently, and the agent cansuccessfully explore 3D maze environment with relatively short training time and small memory consumption.

Description

technical field [0001] The invention belongs to the field of reinforcement learning and deep learning, and mainly relates to a method for exploring a 3D maze by an agent based on deep reinforcement learning. Based on this scene, we can evaluate the training time of various deep reinforcement learning models, memory loss and the ability of the agent to explore the maze stability in the process. Background technique [0002] Reinforcement Learning (RL, Reinforcement Learning) is considered to be one of the core technologies for designing artificial intelligence systems. Reinforcement learning originated from the research of behavioral psychology, which largely imitates the learning mode of intelligent creatures, so that the agent (Agent) with reinforcement learning ability gradually learns the most effective interaction with the environment from its own experience. way, rather than telling the agent how to interact with the environment in advance. The agent's goal for each i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 李玉鑑聂小广刘兆英张婷
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products