8 papers · 1 filter
KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning
Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev +1
Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle mu…
VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models
Egor Cherepanov, Nikita Kachaev, Daniil Zelezetsky +6
Vision-language-action (VLA) models predict chunks of future actions from the current observation, an assumption that fails under partial observability, where decisions depend on i…
ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems
Egor Cherepanov, Alexey K. Kovalev, Aleksandr I. Panov
Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches…
Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
Egor Cherepanov, Nikita Kachaev, Alexey K. Kovalev +1
Memory is crucial for enabling agents to tackle complex tasks with temporal and spatial dependencies. While many reinforcement learning (RL) algorithms incorporate memory, the fiel…
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
Egor Cherepanov, Nikita Kachaev, Artem Zholus +2
The incorporation of memory into agents is essential for numerous tasks within the domain of Reinforcement Learning (RL). In particular, memory is paramount for tasks that require…
Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning
Oleg Shchendrigin, Egor Cherepanov, Alexey K. Kovalev +1
Effective decision-making in the real world depends on memory that is both stable and adaptive: environments change over time, and agents must retain relevant information over long…