Benutzer: Gast  Login
Titel:

Hindsight Experience Replay with Evolutionary Decision Trees for Curriculum Goal Generation

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Sayar, Erdi; Vintaykin, Vladislav; Iacca, Giovanni; Knoll, Alois
Abstract:
Reinforcement learning (RL) algorithms often require a significant number of experiences to learn a policy capable of achieving desired goals in multi-goal robot manipulation tasks with sparse rewards. Hindsight Experience Replay (HER) is an existing method that improves learning efficiency by using failed trajectories and replacing the original goals with hindsight goals that are uniformly sampled from the visited states. However, HER has a limitation: the hindsight goals are mostly near the in...     »
Herausgeber:
Smith, Stephen; Correia, João; Cintrano, Christian
Kongress- / Buchtitel:
Applications of Evolutionary Computation
Verlag / Institution:
Springer Nature Switzerland
Verlagsort:
Cham
Jahr:
2024
Seiten:
3--18
Print-ISBN:
978-3-031-56855-8
 BibTeX