Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Blier, L��onard"'
Autor:
Blier, L��onard, Ollivier, Yann
In multi-goal reinforcement learning (RL) settings, the reward for each goal is sparse, and located in a small neighborhood of the goal. In large dimension, the probability of reaching a reward vanishes and the agent receives little learning signal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::62065150628e69f2955157c3e4440ef0
http://arxiv.org/abs/2106.08863
http://arxiv.org/abs/2106.08863
