Ali Rahimi-Kalahroudi

Researcher, Mila - Quebec Artificial Intelligence Institute

Joined

February 2022

Names

Ali Rahimi-Kalahroudi (Preferred)

Emails

****@mila.quebec (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Researcher

Mila - Quebec Artificial Intelligence Institute (mila.quebec)

2024 – 2026

MS student

Mila - Quebec Artificial Intelligence Institute (mila.quebec)

2021 – 2023

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Steering Large Language Model Activations in Sparse Spaces
Reza Bayat, Ali Rahimi-Kalahroudi, Mohammad Pezeshki, Sarath Chandar, Pascal Vincent
- COLM 2025
- Readers: Everyone
Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning
Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Harm van Seijen, Sarath Chandar
- 2023 (modified: 17 Apr 2023)
- CoRR 2023
- Readers: Everyone
Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning
Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Harm van Seijen, Sarath Chandar
- 08 Oct 2022 (modified: 08 Feb 2026)
- Deep RL Workshop 2022
- Readers: Everyone
Replay Buffer with Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning
Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Harm van Seijen, Sarath Chandar
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
Yi Wan, Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Sarath Chandar, Harm van Seijen
- Published: 23 Apr 2022, Last Modified: 26 May 2025
- ALOE@ICLR2022 Spotlight
- Readers: Everyone
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
Yi Wan, Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Sarath Chandar, Harm van Seijen
- 2022 (modified: 17 Apr 2023)
- CoRR 2022
- Readers: Everyone
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
Yi Wan, Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Sarath Chandar, Harm van Seijen
- 2022 (modified: 17 Apr 2023)
- ICML 2022
- Readers: Everyone

Ali Rahimi-Kalahroudi

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Steering Large Language Model Activations in Sparse Spaces

Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning

Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning

Replay Buffer with Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods

Co-Authors