Davide Maran
8 papers · 2022–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (19) π Interdisciplinary Bridge π Cross-Pollinator (11) π Renaissance Researcher (5) π§ Keyword Pioneer
π
Conference Polyglot
(5)
π
Keyword Champion
(2)
β‘
Prolific Year
(6)
Conferences
AAAI (2)
ICML (2)
NIPS (2)
AISTATS (1)
COLT (1)
Top co-authors
Keywords
regret bound
(3)
markov decision process
(3)
online learning
(3)
reinforcement learning
(3)
multi-armed bandit
(2)
function approximation
(2)
online algorithm
(2)
no-regret algorithm
(2)
imitation learning
(2)
optimal control
(1)
value iteration
(1)
stochastic reward
(1)
stochastic process
(1)
online learning algorithm
(1)
adversarial setting
(1)
no-regret learning
(1)
delayed reinforcement learning
(1)
continuous mdp
(1)
local linearity
(1)
behavioral cloning
(1)
Papers
No-Regret Reinforcement Learning in Smooth MDPs
ICML 2024
Bandits with Ranking Feedback
NIPS 2024
Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs
COLT 2024
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs
NIPS 2024
Online Markov Decision Processes Configuration with Continuous Decision Space
AAAI 2024
Autoregressive Bandits
AISTATS 2024
Tight Performance Guarantees of Imitator Policies with Continuous Actions
AAAI 2023
Delayed Reinforcement Learning by Imitation
ICML 2022