5 papers
Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning
Aditya Narendra, Mukhammadrizo Maribjonov, Dmitry Makarov +2
This paper introduces Knowledge Graph based Massively Multi-task Model-based Policy Optimization (KG-M3PO), a framework for multi-task robotic manipulation in partially observable…
Mind and Motion Aligned: A Joint Evaluation IsaacSim Benchmark for Task Planning and Low-Level Policies in Mobile Manipulation
Nikita Kachaev, Andrei Spiridonov, Andrey Gorodetsky +8
Benchmarks are crucial for evaluating progress in robotics and embodied AI. However, a significant gap exists between benchmarks designed for high-level language instruction follow…
M3PO: Massively Multi-Task Model-Based Policy Optimization
Aditya Narendra, Dmitry Makarov, Aleksandr Panov
We introduce Massively Multi-Task Model-Based Policy Optimization (M3PO), a scalable model-based reinforcement learning (MBRL) framework designed to address sample inefficiency in…
TOCALib: Optimal control library with interpolation for bimanual manipulation and obstacles avoidance
Yulia Danik, Dmitry Makarov, Aleksandra Arkhipova +2
The paper presents a new approach for constructing a library of optimal trajectories for two robotic manipulators, Two-Arm Optimal Control and Avoidance Library (TOCALib). The opti…
Benchmarking the Full-Order Model Optimization Based Imitation in the Humanoid Robot Reinforcement Learning Walk
Ekaterina Chaikovskaya, Inna Minashina, Vladimir Litvinenko +4
When a gait of a bipedal robot is developed using deep reinforcement learning, reference trajectories may or may not be used. Each approach has its advantages and disadvantages, an…