Aleksandr Panov

Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning

ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems

Recurrent Action Transformer with Memory

Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding

Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation

LoLoRA: Locally Fine-Tuned Low Rank Adapters

Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning

Recurrent Action Transformer with Memory

Learning Successor Features with Distributed Hebbian Temporal Memory

POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding

Imagine to Ensure Safety in Hierarchical Reinforcement Learning

Recurrent Action Transformer with Memory

Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation

Semantic Object Navigation with Segmenting Decision Transformer