Zobrazeno 1 - 10
of 214
pro vyhledávání: '"Edelkamp, Stefan"'
This paper presents a novel method for learning reward functions for robotic motions by harnessing the power of a CLIP-based model. Traditional reward function design often hinges on manual feature engineering, which can struggle to generalize across
Externí odkaz:
http://arxiv.org/abs/2311.03485
In imitation learning for planning, parameters of heuristic functions are optimized against a set of solved problem instances. This work revisits the necessary and sufficient conditions of strictly optimally efficient heuristics for forward search al
Externí odkaz:
http://arxiv.org/abs/2310.19463
Optimization of heuristic functions for the A* algorithm, realized by deep neural networks, is usually done by minimizing square root loss of estimate of the cost to goal values. This paper argues that this does not necessarily lead to a faster searc
Externí odkaz:
http://arxiv.org/abs/2209.05206
Learning a well-informed heuristic function for hard task planning domains is an elusive problem. Although there are known neural network architectures to represent such heuristic knowledge, it is not obvious what concrete information is learned and
Externí odkaz:
http://arxiv.org/abs/2112.01918
Autor:
Edelkamp, Stefan
Skat is a fascinating combinatorial card game, show-casing many of the intrinsic challenges for modern AI systems such as cooperative and adversarial behaviors (among the players), randomness (in the deal), and partial knowledge (due to hidden cards)
Externí odkaz:
http://arxiv.org/abs/2104.02997
Autor:
Edelkamp, Stefan
Assessing the skill level of players to predict the outcome and to rank the players in a longer series of games is of critical importance for tournament play. Besides weaknesses, like an observed continuous inflation, through a steadily increasing pl
Externí odkaz:
http://arxiv.org/abs/2104.05422