Scool

95 posts

Scool

Scool

@InriaScool

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".

Lille, France 加入时间 Kasım 2020
105 关注346 粉丝
Scool
Scool@InriaScool·
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
Scool tweet media
English
0
0
2
119
Scool
Scool@InriaScool·
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.
Scool tweet media
English
1
0
2
165
Scool
Scool@InriaScool·
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
Scool tweet media
English
1
0
3
281
Scool
Scool@InriaScool·
Congratulations to @tuanquangdam, Odalric, and Emilie on their work to address biased value function estimation in #MCTS using power means. 🥳 #UAI2024 @Inria_Lille @RechercheUlille
Tuan Dam@tuanquangdam

#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: arxiv.org/pdf/2406.02235

English
0
0
3
248
Scool 已转推
Debabrota Basu
Debabrota Basu@BasuDebabrota·
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.
Debabrota Basu tweet media
English
0
2
6
365
Scool
Scool@InriaScool·
The submission link is #tab-active-submissions" target="_blank" rel="nofollow noopener">openreview.net/group?id=rl-co…. Contact @kohler_hector and the organisers if you have any query.
English
0
1
0
150
Scool
Scool@InriaScool·
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. 👉shorturl.at/ebTkX
English
1
1
1
193
Scool
Scool@InriaScool·
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
Scool tweet media
English
0
0
3
72
Scool
Scool@InriaScool·
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
Scool tweet media
English
1
0
7
182
Scool
Scool@InriaScool·
@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
Scool tweet media
English
0
0
3
75
Scool
Scool@InriaScool·
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.
Scool tweet media
English
1
0
4
428
Scool
Scool@InriaScool·
Today @NeurIPSConf, visit the #WANT workshop to know mode about tools and algorithms to make deep network training computationally friendly and resource efficient. #NeurIPS2023
Scool@InriaScool

@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 want-ai-hpc.github.io #HPC #NeurIPS23

English
0
1
3
335
Scool
Scool@InriaScool·
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
Scool tweet media
English
0
0
3
133
Scool
Scool@InriaScool·
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
Scool tweet media
English
0
0
2
144

发现

@tuanquangdam @icmlconf @Inria_Lille @RechercheUlille @achraf_azize @BasuDebabrota @GuillaumeAP @kohler_hector