TY  - CONF
TI  - Deep reinforcement learning : a study of the CartPole problem
ID  - acta61754
T2  - Conference of PhD students in computer science (11.) (2018) (Szeged)
N1  - Bibliogr.: 20. p. ; összefoglalás angol nyelven
N2  - One of the major challenges of artificial intelligence is to learn solving tasks which are considered to be challenging for even a human. Reinforcement learning is the most general learning framework among the three main type of learning methods: supervised, unsupervised and reinforcement learning. Most of the problems can easily fit into this framework. Experience shows that a lot of machine learning methods with non-linear function approximators suffers from instability regarding convergence. Reinforcement learning is more prone to diverge due to its ability to change the structure of its training data by modifying the way how it interacts with the environment. In this paper we investigate the divergence issue of DQN on the CartPole problem in terms of the algorithm?s parameters. Instead of the usual approach we do not focus on the successful trainings but instead we focus on the dark side where the algorithm fails on such an easy problem like CartPole. The motivation is to gain some further insight into the nature of the divergence issues on a specific problem.
UR  - http://acta.bibl.u-szeged.hu/61754/
VL  - 11
SP  - 17
Y1  - 2018///
AV  - public
A1  -  Budai Ádám
A1  -  Csorba Kristóf
KW  - Számítástechnika - el?adáskivonat
KW  -  Algoritmus - el?adáskivonat
EP  - 20
ER  -