Title | ||
---|---|---|
Compulsory Flow Q-Learning: an RL algorithm for robot navigation based on partial-policy and macro-states |
Abstract | ||
---|---|---|
Reinforcement Learning is carried out on-line, through trial-and-error interactions of the agent with the environment, which can be very time consuming when considering robots. In this paper we contribute a new learning algorithm, CFQ- Learning, which uses macro-states, a low-resolution discretisation of the state space, and a partial-policy to get around obstacles, both of them based on the complexity of the environment structure. The use of macro-states avoids convergence of algorithms, but can accelerate the learning process. In the other hand, partial-policies can guarantee that an agent fulfils its task, even through macro-state. Experiments show that the CFQ-Learning performs a good balance between policy quality and learning rate. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1590/S0104-65002009000300007 | J. Braz. Comp. Soc. |
Keywords | Field | DocType |
machine learning,reinforcement learning,abstraction,partial-policy,macro-states. | Robot learning,Instance-based learning,Stability (learning theory),Active learning (machine learning),Computer science,Q-learning,Algorithm,Unsupervised learning,Artificial intelligence,Reinforcement learning,Learning classifier system | Journal |
Volume | Issue | ISSN |
15 | 3 | 1678-4804 |
Citations | PageRank | References |
0 | 0.34 | 13 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Valdinei Freire da Silva | 1 | 25 | 6.86 |
Anna Helena Reali Costa | 2 | 192 | 31.97 |