… Also within the formalism of optimal control one can give up optimality and, instead, design controllers that are more robust to mismatches between model and reallife, namely by …
… autonomous learning. We give a summary of the state-of-the-art of reinforcementlearning in … Three recent examples for the application of reinforcementlearning to real-world robots are …
… He is passionate about popularizing artificial intelligence technologies and established TensorLayer, a deep learning and reinforcementlearning library for scientists and engineers, …
In this paper, we introduce the first learning-based planner to drive a car in dense, urban traffic using Inverse ReinforcementLearning (IRL). Our planner, DriveIRL, generates a diverse …
… Identification and definition of real-world challenges: Our main goal is to more clearly define the issues reinforcementlearning is having when dealing with real systems. By making …
J Lin, Z Ma, R Gomez, K Nakamura, B He, G Li - IEEE Access, 2020 - ieeexplore.ieee.org
… learn from feedback via unimodal or multimodal sensory input. This paper reviews methods for interactive reinforcementlearning agent to learn … human-human interaction in the reallife. …
… games to solving complex real-life problems in autonomous … selecting the appropriate reinforcementlearning algorithm that … and classify reinforcementlearning algorithms according to …
… how inverse reinforcementlearning (IRL) can be employed to retrieve the reward function implicitly optimized by expert agents acting in real applications. Scaling IRL to real-world …
Y Li - arXiv preprint arXiv:1908.06973, 2019 - arxiv.org
… REINFORCEMENTLEARNING FOR REALLIFE We organized the ICML 2019 Workshop on ReinforcementLearning for RealLife … theoretical issues in applying RL to reallife scenarios. …