Scool is a #MachineLearning research team in @Inria & CRIStAL interested in designing algorithms that learn & adapt on-the-go. It is the new avatar of "SequeL".
4/n Alena, Thomas, Phillipe & Bruno motivated by uniqueness ambiguity of value func as a solution to HJB eqn in CTRL, propose to approximate the value func by training a PINN through a specific scheduling iterative process that constraints it to converge to the viscosity solution
1/n Today, we concluded @icmlconf with 4 presentations at the #FORLAC workshop conjoining RL theory and Control. Following their UAI work, @tuanquangdam, Odalric & Emilie on their work to address biased value function estimation in #MCTS using power means. #ICML2024@Inria_Lille
3/n MCTS with deep NN shows promising performance in deterministic envs, but fails in stochastic envs. @tuanquangdam, Odarlic & Brahim propose CATS & PATS, leveraging TS to handle selection randomness. They achieve regret guarantees as well as good performance in stochastic envs.
#UAI2024 Interested in how power mean can enhance value function estimation in tree search methods? Learn about our approach to solving biases in MCTS for stochastic settings. Join us tomorrow at 4:30 PM in the Exhibition room, building 20.
Paper: https://t.co/ZH8M3glKsT
We've derived tight lower and upper bounds for differentially private finite-armed & linear bandits, while we lack the same for contextual bandits. At #COLT2024, @achraf_azize presents open problems in contextual bandits with privacy. @BasuDebabrota@Inria_Lille@RechercheUlille
It's fun to revisit the sanctum sanctorum: how does a brain learn? Today at Convention on Mathematics of #Neuroscience & #AI, @GuillaumeAP presents our work with @AdityaGilra on how to design a bio-plausible learning rule rather than backprop type methods to learn a time series.
We are glad to announce the 1st edition of Workshop on Interpretable Policies in Reinforcement Learning (InterpPol) @RL_Conference. Plz submit your original/published papers on Interpretable/Explainable RL, Policy Distillation, Formal Verification & RL.
👉https://t.co/G2QyW2XtlG
2/2 If each arm has multiple objectives, how to identify an arm whose mean vector is not worse than any of the others. Tomorrow @aistats_conf, Emilie & Cyrille will present "first" algo to detect such pareto sets with finite budget & bandit feedback. @RechercheUlille@Inria_Lille
1/2 Is exploration harder if we've constraints on policies? No, depends on how constraints change the geometry of alternating set. Today @aistats_conf, @BasuDebabrota & collaborators present insights & algorithms for pure exploration with constraints. #AISTATS2024@chalmersuniv
1/2 To define privacy in bandits, we have to ask what are the input and output of a bandit algorithm? What differs if the adversary is interactive or passive? @achraf_azize & @BasuDebabrota address these in their work https://t.co/z93Cd3R1G0.
@TmlrOrg we address the corrupted bandit problem, i.e. a stochastic multi-armed bandit problem with unknown reward distributions, which are heavy-tailed and corrupted by a history-independent adversary or Nature. We provide another set of lower bounds and algorithm. #robustness
What happens in a bandit problem if epsilon fraction of feedback are arbitrarily corrupt? What are the new lower bounds on the regret? Can we design an optimal algorithm for #Bandits_corrupted_by_nature? We address this question in two parts.
Today @NeurIPSConf, visit the #WANT workshop to know mode about tools and algorithms to make deep network training computationally friendly and resource efficient. #NeurIPS2023
@InriaScool's Alena Shilova with a team from @nvidia@Inria & @ufrj is organising #WANT workshop @NeurIPSConf. If interested in tools & algorithms to make training computationally efficient & scalable with optimal resource utilisation,visit https://t.co/S9aTClu5YU #HPC#NeurIPS23
What happens if you've multiple objectives/rewards for each arm? How can you find pareto set with bandits? At 5PM @NeurIPSConf, Cyrille'll present an adaptive & sequential sampling to identify Pareto set (or a relaxed Pareto set) of multivariate distributions #NeurIPS23#Bandit
What happens if you've multiple objectives/rewards for each arm? How can you find pareto set with bandits? At 5PM @NeurIPSConf, Cyrille'll present an adaptive & sequential sampling to identify Pareto set (or a relaxed Pareto set) of multivariate distributions. #NeurIPS23#Bandit