List of discussions. Showing 53 of 53 discussions
Status Discussion Started by Last post Replies Actions
Gradients
Picture of Jakhongir Saydaliev
Jakhongir Saydaliev
Picture of Jakhongir Saydaliev
Jakhongir Saydaliev
 2
Exam 2022, question 4) (iii)
Picture of Robin Patriarca
Robin Patriarca
Picture of Michael Alain Hauri
Michael Alain Hauri
 1
Model-free RL, policy gradient
Picture of Maria Yuffa Meshcheryakova
Maria Yuffa Meshcheryakova
Picture of Sophia Becker
Sophia Becker
 1
Weight updates in A2C algorithms
Picture of Gal Sebastian Pascual
Gal Sebastian Pascual
Picture of Gal Sebastian Pascual
Gal Sebastian Pascual
 0
Model-based RL criteria for exploration term
Picture of Maria Yuffa Meshcheryakova
Maria Yuffa Meshcheryakova
Picture of Ariane Delrocq
Ariane Delrocq
 1
Incorrectness in solution Exercise 9 b)
Picture of Ali Bakly
Ali Bakly
Picture of Ariane Delrocq
Ariane Delrocq
 2
Off-policy vs On-policy training
Picture of Amine Belghmi
Amine Belghmi
Picture of Ariane Delrocq
Ariane Delrocq
 1
Questions for the exams
Picture of David Friou
David Friou
Picture of Sophia Becker
Sophia Becker
 1
Format of handwritten notes in final exam
Picture of Jannik Paul Endres
Jannik Paul Endres
Picture of Sophia Becker
Sophia Becker
 3
DDPG
Picture of Nicolás Hernán Reátegui Rodríguez
Nicolás Hernán Reátegui Rodríguez
Picture of Ali Bakly
Ali Bakly
 1
MP2 fraud detection interviews
Picture of Orélian Kohler
Orélian Kohler
Picture of Sophia Becker
Sophia Becker
 1
Appendix
Picture of Maria Yuffa Meshcheryakova
Maria Yuffa Meshcheryakova
Picture of Maria Yuffa Meshcheryakova
Maria Yuffa Meshcheryakova
 0
MP1: agent forget optimal policy
Picture of Lenny Del Zio
Lenny Del Zio
Picture of Lenny Del Zio
Lenny Del Zio
 0
Wrong submission
Picture of Nicolás Hernán Reátegui Rodríguez
Nicolás Hernán Reátegui Rodríguez
Picture of Nicolás Hernán Reátegui Rodríguez
Nicolás Hernán Reátegui Rodríguez
 1
MP1 - RND Normalization
Picture of Gaston Emil Wolfart
Gaston Emil Wolfart
Picture of Maria Yuffa Meshcheryakova
Maria Yuffa Meshcheryakova
 2
Mountain Car - DQN auxilary reward loss behaviour
Picture of Jakhongir Saydaliev
Jakhongir Saydaliev
Picture of Lucas Louis Gruaz
Lucas Louis Gruaz
 4
Mountain car mini project
Picture of Thibault Schiesser
Thibault Schiesser
Picture of Lucas Louis Gruaz
Lucas Louis Gruaz
 1
MP2 - Hidden layers
Picture of Thomas Brunet
Thomas Brunet
Picture of Thomas Brunet
Thomas Brunet
 4
Deliverables - Code
Picture of Nicolás Hernán Reátegui Rodríguez
Nicolás Hernán Reátegui Rodríguez
Picture of Sophia Becker
Sophia Becker
 1
fraud detection interview
Picture of Gal Sebastian Pascual
Gal Sebastian Pascual
Picture of Sophia Becker
Sophia Becker
 1
MP2 Clarification on reward stochasticity
Picture of Skander Moalla
Skander Moalla
Picture of Skander Moalla
Skander Moalla
 0
MP1 Project report
Picture of Renqing Cuomao
Renqing Cuomao
Picture of Anja Surina
Anja Surina
 1
MP1
Picture of Aymane Lamyaghri
Aymane Lamyaghri
Picture of Anja Surina
Anja Surina
 1
balancing the rewards
Picture of Amine Belghmi
Amine Belghmi
Picture of Anja Surina
Anja Surina
 1
MP2 clarification on return logging
Picture of Skander Moalla
Skander Moalla
Picture of Skander Moalla
Skander Moalla
 0
MP2 - Sparse Rewards / K workers
Picture of Thomas Brunet
Thomas Brunet
Picture of Skander Moalla
Skander Moalla
 3
Page limit for project (MP2)
Picture of Ali Bakly
Ali Bakly
Picture of Skander Moalla
Skander Moalla
 11
MP1 - Running time
Picture of Gaston Emil Wolfart
Gaston Emil Wolfart
Picture of Tobia Fjellman
Tobia Fjellman
 6
Ex 7.2 a)
Picture of Ali Bakly
Ali Bakly
Picture of Sophia Becker
Sophia Becker
 1
MP2- Detail about the a2c algorithm
Picture of Ali Bakly
Ali Bakly
Picture of Skander Moalla
Skander Moalla
 1
MP2 - A2C Loss plots
Picture of Alexis Leandro Cogne
Alexis Leandro Cogne
Picture of Skander Moalla
Skander Moalla
 1
Stochasticity (MP2)
Picture of Ali Bakly
Ali Bakly
Picture of Skander Moalla
Skander Moalla
 4
MP2-A2C n-step bootstrapping
Picture of Laura Gambaretto
Laura Gambaretto
Picture of Skander Moalla
Skander Moalla
 1
Mp2-3.4: Training batch when the episode is done
Picture of Hyeongdon Moon
Hyeongdon Moon
Picture of Hyeongdon Moon
Hyeongdon Moon
 4
Clarifications on the A2C algorithm (MP2)
Picture of Abigaïl Rebecca Lise Ingster
Abigaïl Rebecca Lise Ingster
Picture of Skander Moalla
Skander Moalla
 1
MP1 - DQN implementation
Picture of Yauheniya Karelskaya
Yauheniya Karelskaya
Picture of Lucas Louis Gruaz
Lucas Louis Gruaz
 1
Project- Dyna algo model
Picture of Alexi Semiz
Alexi Semiz
Picture of Lucas Louis Gruaz
Lucas Louis Gruaz
 1
Functions in the Project description
Picture of Jakhongir Saydaliev
Jakhongir Saydaliev
Picture of Lucas Louis Gruaz
Lucas Louis Gruaz
 1
Debugger failed on my notebook
Picture of Abigaïl Rebecca Lise Ingster
Abigaïl Rebecca Lise Ingster
Picture of Abigaïl Rebecca Lise Ingster
Abigaïl Rebecca Lise Ingster
 0
MP2 - Question 3.1
Picture of Thomas Brunet
Thomas Brunet
Picture of Thomas Brunet
Thomas Brunet
 4
MP2, Standard Deviation in Task 4.1
Picture of Ali Bakly
Ali Bakly
Picture of Skander Moalla
Skander Moalla
 3
Week 10 exercises
Picture of Antoine Nicolas Schutz
Antoine Nicolas Schutz
Picture of Sophia Becker
Sophia Becker
 1
(Project) n-step A2C
Picture of Ali Bakly
Ali Bakly
Picture of Skander Moalla
Skander Moalla
 3
Incorrect equation in Lecture 8, n-step a2c?
Picture of Ali Bakly
Ali Bakly
Picture of Ali Bakly
Ali Bakly
 0
Inconsistent A2C convergence to optimal policy with 1 worker and no batches
Picture of Alexei Ivan Nicolai Igor Ermochkine
Alexei Ivan Nicolai Igor Ermochkine
Picture of Skander Moalla
Skander Moalla
 1
Recommended Conda installation
Picture of Skander Moalla
Skander Moalla
Picture of Skander Moalla
Skander Moalla
 0
Switchtube videos not available
Picture of Gal Sebastian Pascual
Gal Sebastian Pascual
Picture of Sophia Becker
Sophia Becker
 2
Solution to Computer Exercises 1 - Bug with recent matplotlib versions
Picture of Skander Moalla
Skander Moalla
Picture of Skander Moalla
Skander Moalla
 0
Exercise 5-4.c
Picture of Jakhongir Saydaliev
Jakhongir Saydaliev
Picture of Ariane Delrocq
Ariane Delrocq
 1
Exercise 5 3.c
Picture of Jakhongir Saydaliev
Jakhongir Saydaliev
Picture of Ariane Delrocq
Ariane Delrocq
 1
Final exam date?
Picture of David Kalajdzic
David Kalajdzic
Picture of Sophia Becker
Sophia Becker
 1
Miniproject group
Picture of Ahmad Bilal Kakar
Ahmad Bilal Kakar
Picture of Sophia Becker
Sophia Becker
 2
Lecture Recordings
Picture of Renqing Cuomao
Renqing Cuomao
Picture of Renqing Cuomao
Renqing Cuomao
 0