In a previous paper, we proposed a solution to motion planning of a mobile robot. In our approach, we formulated the problem as a discrete optimization problem at each time step. To solve the optimization problem, we used an objective function consisting of a goal term, a smoothness term and a collision term. In this paper, we propose a theoretical method using reinforcement learning for adjusting weight parameters in the objective functions. However, the conventional Q-learning method cannot be applied to a non-Markov decision process, which is caused by the smoothness term. Thus, we applied William's learning algorithm, episodic REINFORCE, to derive a learning rule for the weight parameters. This maximizes a value function stochastically. We verified the learning rule by some experiments.
|Number of pages||6|
|Publication status||Published - 2001 Jan 1|
|Event||2001 IEEE International Symposium on Assembly and Task Planning (ISATP2001) - Fukuoka, Japan|
Duration: 2001 May 28 → 2001 May 29
|Conference||2001 IEEE International Symposium on Assembly and Task Planning (ISATP2001)|
|Period||01/5/28 → 01/5/29|
ASJC Scopus subject areas