Bilinear classes: A structural framework for provable generalization in rl
Abstract This work introduces Bilinear Classes, a new structural framework, which permit
generalization in reinforcement learning in a wide variety of settings through the use of …
generalization in reinforcement learning in a wide variety of settings through the use of …
Representation learning for online and offline rl in low-rank mdps
On information gain and regret bounds in gaussian process bandits
Consider the sequential optimization of an expensive to evaluate and possibly non-convex
objective function $ f $ from noisy feedback, that can be considered as a continuum-armed …
objective function $ f $ from noisy feedback, that can be considered as a continuum-armed …
Mitigating covariate shift in imitation learning via offline data with partial coverage
This paper studies offline Imitation Learning (IL) where an agent learns to imitate an expert
demonstrator without additional online environment interactions. Instead, the learner is …
demonstrator without additional online environment interactions. Instead, the learner is …
Distributionally robust model-based reinforcement learning with large state spaces
Three major challenges in reinforcement learning are the complex dynamical systems with
large state spaces, the costly data acquisition processes, and the deviation of real-world …
large state spaces, the costly data acquisition processes, and the deviation of real-world …
Model-based rl with optimistic posterior sampling: Structural conditions and sample complexity
We propose a general framework to design posterior sampling methods for model-based
RL. We show that the proposed algorithms can be analyzed by reducing regret to Hellinger …
RL. We show that the proposed algorithms can be analyzed by reducing regret to Hellinger …
On function approximation in reinforcement learning: Optimism in the face of large state spaces
The classical theory of reinforcement learning (RL) has focused on tabular and linear
representations of value functions. Further progress hinges on combining RL with modern …
representations of value functions. Further progress hinges on combining RL with modern …
Optimal exploration for model-based rl in nonlinear systems
Learning to control unknown nonlinear dynamical systems is a fundamental problem in
reinforcement learning and control theory. A commonly applied approach is to first explore …
reinforcement learning and control theory. A commonly applied approach is to first explore …