Mastering Memory Tasks with World Models

1 code implementation • 7 Mar 2024 • Mohammad Reza Samsami, Artem Zholus, Janarthanan Rajendran, Sarath Chandar

Through a diverse set of illustrative tasks, we systematically demonstrate that R2I not only establishes a new state-of-the-art for challenging memory and credit assignment RL tasks, such as BSuite and POPGym, but also showcases superhuman performance in the complex memory domain of Memory Maze.

Model-based Reinforcement Learning

Causal Imitative Model for Autonomous Driving

1 code implementation • 7 Dec 2021 • Mohammad Reza Samsami, Mohammadhossein Bahari, Saber Salehkaleybar, Alexandre Alahi

CIM explicitly discovers the causal model and utilizes it to train the policy.

Autonomous Driving Imitation Learning +1

Distributed Deep Reinforcement Learning: An Overview

no code implementations • 22 Nov 2020 • Mohammad Reza Samsami, Hossein Alimadad

Deep reinforcement learning (DRL) is a very active research area.

Multi-Task Learning reinforcement-learning +1

Recognizing Arrow Of Time In The Short Stories

1 code implementation • WS 2019 • Fahimeh Hosseini, Hosein Fooladi, Mohammad Reza Samsami

Recognizing arrow of time in short stories is a challenging task.