Nearly minimax optimal reinforcement learning for linear mixture markov decision processes
We study reinforcement learning (RL) with linear function approximation where the
underlying transition probability kernel of the Markov decision process (MDP) is a linear …
underlying transition probability kernel of the Markov decision process (MDP) is a linear …
VOL: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation
We study time-inhomogeneous episodic reinforcement learning (RL) under general function
approximation and sparse rewards. We design a new algorithm, Variance-weighted …
approximation and sparse rewards. We design a new algorithm, Variance-weighted …
Nearly minimax optimal reinforcement learning with linear function approximation
We study reinforcement learning with linear function approximation where the transition
probability and reward functions are linear with respect to a feature mapping $\boldsymbol …
probability and reward functions are linear with respect to a feature mapping $\boldsymbol …
Best policy identification in linear mdps
J Taupin, Y Jedra, A Proutiere - 2023 59th Annual Allerton …, 2023 - ieeexplore.ieee.org
We consider the problem of best policy identification in discounted Linear Markov Decision
Processes in the fixed confidence setting, under both generative and forward models. We …
Processes in the fixed confidence setting, under both generative and forward models. We …
Best policy identification in discounted linear mdps
J Taupin, Y Jedra, A Proutiere - Sixteenth European Workshop on …, 2023 - openreview.net
We consider the problem of best policy identification in discounted Linear Markov Decision
Processes in the fixed confidence setting, under both generative and forward models. We …
Processes in the fixed confidence setting, under both generative and forward models. We …
Statistical Learning in Linearly Structured Systems: Identification, Control, and Reinforcement Learning
Y Jedra - 2023 - diva-portal.org
In this thesis, we investigate the design and statistical efficiency of learning algorithms in
systems with a linear structure. This study is carried along three main domains, namely …
systems with a linear structure. This study is carried along three main domains, namely …