Inventor · disambiguated record
Bilal Piot
Also filed as: PIOT BILAL
6 granted patents·9 pending applications·3 citations·filing 2018–2024
69Inventor score
Files withDEEPMIND TECH LTD15
Top patents by PatentIndex Score
15 records- 0175US11868882B2Training action selection neural networks using apprenticeshipDEEPMIND TECH LTD·Filed 2018·Granted Jan 9, 2024·3 cites·20 claims
- 0274US2025148774A1Reinforcement learning for active sequence processingDEEPMIND TECH LTD·Filed 2024·Application pending·0 cites
- 0367US11886997B2Training action selection neural networks using apprenticeshipDEEPMIND TECH LTD·Filed 2022·Granted Jan 30, 2024·0 cites·20 claims
- 0461US12175737B2Reinforcement learning for active sequence processingDEEPMIND TECH LTD·Filed 2020·Granted Dec 24, 2024·0 cites·31 claims
- 0560US2025371413A1Tied Preference Optimization for Sequence Processing ModelsDEEPMIND TECH LTD·Filed 2024·Application pending·0 cites
- 0660US2024028866A1Jointly learning exploratory and non-exploratory action selection policiesDEEPMIND TECH LTD·Filed 2023·Application pending·0 cites
- 0757US11977983B2Noisy neural network layers with noise parametersDEEPMIND TECH LTD·Filed 2020·Granted May 7, 2024·0 cites·20 claims
- 0854US2025259073A1Reinforcement learning through preference feedbackDEEPMIND TECH LTD·Filed 2024·Application pending·0 cites
- 0952US10839293B2Noisy neural network layers with noise parametersDEEPMIND TECH LTD·Filed 2019·Granted Nov 17, 2020·0 cites·22 claims
- 1050US11714990B2Jointly learning exploratory and non-exploratory action selection policiesDEEPMIND TECH LTD·Filed 2020·Granted Aug 1, 2023·0 cites·18 claims
- 1149US2025209338A1Exploration by bootstrapped predictionDEEPMIND TECH LTD·Filed 2023·Application pending·0 cites
- 1244US2021383225A1Self-supervised representation learning using bootstrapped latent representationsDEEPMIND TECH LTD·Filed 2021·Application pending·0 cites
- 1343US2023083486A1Learning environment representations for agent control using predictions of bootstrapped latentsDEEPMIND TECH LTD·Filed 2021·Application pending·0 cites
- 1441US2023059004A1Reinforcement learning with adaptive return computation schemesDEEPMIND TECH LTD·Filed 2021·Application pending·0 cites
- 1535US2022092456A1Controlling an agent to explore an environment using observation likelihoodsDEEPMIND TECH LTD·Filed 2020·Application pending·0 cites
Join the waitlist — get patent alerts
Get an alert when Bilal Piot files or is granted a new patent.
We store only your email — no account needed. See our privacy policy.
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →