4 papers
When Robots Say No: The Empathic Ethical Disobedience Benchmark
Dmytro Kuzmenko, Nadiya Shvai
Robots must balance compliance with safety and social expectations as blind obedience can cause harm, while over-refusal erodes trust. Existing safe reinforcement learning (RL) ben…
TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents
Dmytro Kuzmenko, Nadiya Shvai
We present a novel approach to knowledge transfer in model-based reinforcement learning, addressing the critical challenge of deploying large world models in resource-constrained e…
MoIRA: Modular Instruction Routing Architecture for Multi-Task Robotics
Dmytro Kuzmenko, Nadiya Shvai
Mixture-of-Experts (MoE) approaches have recently gained traction in robotics applications due to their ability to dynamically allocate computational resources and specialize sub-n…
Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning
Dmytro Kuzmenko, Nadiya Shvai
We propose an efficient knowledge transfer approach for model-based reinforcement learning, addressing the challenge of deploying large world models in resource-constrained environ…