Alert button
Picture for Ahmed Touati

Ahmed Touati

Alert button

Score Models for Offline Goal-Conditioned Reinforcement Learning

Nov 03, 2023
Harshit Sikchi, Rohan Chitnis, Ahmed Touati, Alborz Geramifard, Amy Zhang, Scott Niekum

Viaarxiv icon

A State Representation for Diminishing Rewards

Sep 07, 2023
Ted Moskovitz, Samo Hromadka, Ahmed Touati, Diana Borsa, Maneesh Sahani

Figure 1 for A State Representation for Diminishing Rewards
Figure 2 for A State Representation for Diminishing Rewards
Figure 3 for A State Representation for Diminishing Rewards
Figure 4 for A State Representation for Diminishing Rewards
Viaarxiv icon

Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees

Oct 24, 2022
Andrea Tirinzoni, Matteo Papini, Ahmed Touati, Alessandro Lazaric, Matteo Pirotta

Figure 1 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Figure 2 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Figure 3 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Figure 4 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Viaarxiv icon

Does Zero-Shot Reinforcement Learning Exist?

Sep 29, 2022
Ahmed Touati, Jérémy Rapin, Yann Ollivier

Figure 1 for Does Zero-Shot Reinforcement Learning Exist?
Figure 2 for Does Zero-Shot Reinforcement Learning Exist?
Figure 3 for Does Zero-Shot Reinforcement Learning Exist?
Figure 4 for Does Zero-Shot Reinforcement Learning Exist?
Viaarxiv icon

Learning One Representation to Optimize All Rewards

Mar 14, 2021
Ahmed Touati, Yann Ollivier

Figure 1 for Learning One Representation to Optimize All Rewards
Figure 2 for Learning One Representation to Optimize All Rewards
Figure 3 for Learning One Representation to Optimize All Rewards
Figure 4 for Learning One Representation to Optimize All Rewards
Viaarxiv icon

Efficient Learning in Non-Stationary Linear Markov Decision Processes

Oct 24, 2020
Ahmed Touati, Pascal Vincent

Figure 1 for Efficient Learning in Non-Stationary Linear Markov Decision Processes
Viaarxiv icon

Maximum Reward Formulation In Reinforcement Learning

Oct 08, 2020
Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall, Sahir, Raviteja Chunduru, Ahmed Touati, Sriram Ganapathi Subramanian, Matthew E. Taylor, Sarath Chandar

Figure 1 for Maximum Reward Formulation In Reinforcement Learning
Figure 2 for Maximum Reward Formulation In Reinforcement Learning
Figure 3 for Maximum Reward Formulation In Reinforcement Learning
Figure 4 for Maximum Reward Formulation In Reinforcement Learning
Viaarxiv icon

Sharp Analysis of Smoothed Bellman Error Embedding

Jul 07, 2020
Ahmed Touati, Pascal Vincent

Viaarxiv icon

TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?

Jul 06, 2020
Joshua Romoff, Peter Henderson, David Kanaa, Emmanuel Bengio, Ahmed Touati, Pierre-Luc Bacon, Joelle Pineau

Figure 1 for TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
Figure 2 for TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
Figure 3 for TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
Figure 4 for TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
Viaarxiv icon

Stable Policy Optimization via Off-Policy Divergence Regularization

Mar 09, 2020
Ahmed Touati, Amy Zhang, Joelle Pineau, Pascal Vincent

Figure 1 for Stable Policy Optimization via Off-Policy Divergence Regularization
Figure 2 for Stable Policy Optimization via Off-Policy Divergence Regularization
Figure 3 for Stable Policy Optimization via Off-Policy Divergence Regularization
Figure 4 for Stable Policy Optimization via Off-Policy Divergence Regularization
Viaarxiv icon