101 citations · 214 across the 17 of their papers we have counts for
3 papers · 1 filter
Delayed Feedback in Generalised Linear Bandits Revisited
Benjamin Howson, Ciara Pike-Burke, Sarah Filippi
The stochastic generalised linear bandit is a well-understood model for sequential decision-making problems, with many algorithms achieving near-optimal regret guarantees under imm…
Optimism and Delays in Episodic Reinforcement Learning
Benjamin Howson, Ciara Pike-Burke, Sarah Filippi
There are many algorithms for regret minimisation in episodic reinforcement learning. This problem is well-understood from a theoretical perspective, providing that the sequences o…
Optimism in Reinforcement Learning and Kullback-Leibler Divergence
Sarah Filippi, Olivier Cappé, Aurélien Garivier
We consider model-based reinforcement learning in finite Markov De- cision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by c…