Reinforcement learning, bit by bit
Reinforcement learning agents have demonstrated remarkable achievements in simulated
environments. Data efficiency poses an impediment to carrying this success over to real …
environments. Data efficiency poses an impediment to carrying this success over to real …
Provable and practical: Efficient exploration in reinforcement learning via langevin monte carlo
We present a scalable and effective exploration strategy based on Thompson sampling for
reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling …
reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling …
Ensembles for uncertainty estimation: Benefits of prior functions and bootstrapping
In machine learning, an agent needs to estimate uncertainty to efficiently explore and adapt
and to make effective decisions. A common approach to uncertainty estimation maintains an …
and to make effective decisions. A common approach to uncertainty estimation maintains an …
Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity
We study the problem of online sequential decision-making given auxiliary demonstrations
from experts who made their decisions based on unobserved contextual information. These …
from experts who made their decisions based on unobserved contextual information. These …
[PDF][PDF] Bayesian Model-Free Deep Reinforcement Learning
PR van der Vaart - Proceedings of the 23rd International Conference on …, 2024 - ifaamas.org
Exploration in reinforcement learning remains a difficult challenge. In order to drive
exploration, ensembles with randomized prior functions have recently been popularized to …
exploration, ensembles with randomized prior functions have recently been popularized to …
Bayesian Ensembles for Exploration in Deep Q-Learning
P Van der Vaart, N Yorke-Smith… - The Sixteenth Workshop …, 2024 - openreview.net
Exploration in reinforcement learning remains a difficult challenge. In order to drive
exploration, ensembles with randomized prior functions have recently been popularized to …
exploration, ensembles with randomized prior functions have recently been popularized to …