Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Watahiki, Hayato"'
Transferring learned skills across diverse situations remains a fundamental challenge for autonomous agents, particularly when agents are not allowed to interact with an exact target setup. While prior approaches have predominantly focused on learnin
Externí odkaz:
http://arxiv.org/abs/2407.16912
Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while satisfying a set of prescribed safety constraints. In this study, we p
Externí odkaz:
http://arxiv.org/abs/1909.09540