Egor Cherepanov

Research Scientist (RL, Robotics)

profile_photo.png

Hello! I am a PhD researcher studying memory mechanisms in reinforcement learning and embodied robotics, with a focus on transformer-based sequence models for long-horizon, partially observable tasks.

📰 Latest Updates

Jan 22, 2026
The camera-ready version of our AAMAS paper “Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning” is now available on arXiv.
Jan 21, 2026
KAGE-Bench preprint published
Jan 13, 2026
KAGE-Bench code is now available on GitHub! KAGE-Bench is a pure JAX 2D platformer RL benchmark for visual OOD generalization.
Dec 06, 2025
The paper “Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning” has been accepted to AAMAS-2026.
Dec 03, 2025
Announcing Awesome Memory VLA
Online
Dec 01, 2025
The paper “MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning” has been accepted to WoMAPF Workshop @ AAAI-2026.
Nov 20 - Nov 21, 2025
Attending AIJ 2025
Offline, Moscow, Russia
Oct 24 - Oct 25, 2025
Attending Fall into ML 2025
Offline, Moscow, Russia
Oct 09, 2025
The preprint of our paper “A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control” is now available on arXiv.
Oct 09, 2025
The preprint of our paper “ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL” is now available on arXiv.
Sep 27 - Sep 30, 2025
Attending CoRL-2025
Offline, Seoul, South Korea