Abstract | ||
---|---|---|
In this paper, a model learning method based on tree structures is present to achieve the sample efficiency in stochastic environment. The proposed method is composed of Q-Learning algorithm to form a Dyna agent that can used to speed up learning. The Q-Learning is used to learn the policy, and the proposed method is for model learning. The model builds the environment model and simulates the virtual experience. The virtual experience can decrease the interaction between the agent and the environment and make the agent perform value iterations quickly. Thus, the proposed agent has additional experience for updating the policy. The simulation task, a mobile robot in a maze, is introduced to compare the methods, Q-Learning, Dyna-Q and the proposed method. The result of simulation confirms the proposed method that can achieve the goal of sample efficiency. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/SMC.2013.433 | SMC |
Keywords | Field | DocType |
stochastic environment,q-learning algorithm,environment model,dyna-q architecture,model-based indirect learning method,model learning,additional experience,virtual experience,proposed agent,sample efficiency,dyna agent,decision tree,learning artificial intelligence,stochastic processes,iterative methods,mobile robots,decision trees,multi agent systems | Robot learning,Online machine learning,Active learning (machine learning),Computer science,Iterative method,Multi-agent system,Artificial intelligence,Tree structure,ID3 algorithm,Mobile robot,Machine learning | Conference |
ISSN | Citations | PageRank |
1062-922X | 0 | 0.34 |
References | Authors | |
2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
kaoshing hwang | 1 | 399 | 59.91 |
Wei-Cheng Jiang | 2 | 33 | 9.51 |
Yu-Jen Chen | 3 | 156 | 23.38 |
Weihan Wang | 4 | 19 | 6.08 |