Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Krupnik, Orr"'
Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional task distribu
Externí odkaz:
http://arxiv.org/abs/2403.09859
Adaptable models could greatly benefit robotic agents operating in the real world, allowing them to deal with novel and varying conditions. While approaches such as Bayesian inference are well-studied frameworks for adapting models to evidence, we bu
Externí odkaz:
http://arxiv.org/abs/2310.12862
We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL typically suffe
Externí odkaz:
http://arxiv.org/abs/1901.10251