G Konidaris - Current opinion in behavioral sciences, 2019 - Elsevier
A generally intelligent agent faces a dilemma: it requires a complex sensorimotor space to be capable of solving a wide range of problems, but many tasks are only feasible given the …
We study the sample complexity of model-based reinforcement learning (henceforth RL) in general contextual decision processes that require strategic exploration to find a near …
This book is written for students and researchers in the field of industrial engineering, computer science, operations research, management science, electrical engineering, and …
AL Strehl, L Li, ML Littman - Journal of Machine Learning Research, 2009 - jmlr.org
We study the problem of learning near-optimal behavior in finite Markov Decision Processes (MDPs) with a polynomial number of samples. These “PAC-MDP” algorithms include the …
L Li, ML Littman, TJ Walsh - … of the 25th international conference on …, 2008 - dl.acm.org
We introduce a learning framework that combines elements of the well-known PAC and mistake-bound models. The KWIK (knows what it knows) framework was designed …
In real-world reinforcement learning applications the learner's observation space is ubiquitously high-dimensional with both relevant and irrelevant information about the task at …
The use of robots in society could be expanded by using reinforcement learning (RL) to allow robots to learn and adapt to new situations online. RL is a paradigm for learning …
E Brunskill, L Li - arXiv preprint arXiv:1309.6821, 2013 - arxiv.org
Transferring knowledge across a sequence of reinforcement-learning tasks is challenging, and has a number of important applications. Though there is encouraging empirical …
B Juba, R Stern - Proceedings of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
We consider the problem of learning action models for planning in unknown stochastic environments that can be defined using the Probabilistic Planning Domain Description …