Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot
Viktor Zhumatiy, Faustino Gomez, Marcus Hutter, Juergen Schmidhuber
Abstract
We address the problem of autonomously learning controllers for vision-capable mobile robots. We extend McCallum's (1995) Nearest-Sequence Memory algorithm to allow for general metrics over state-action trajectories. We demonstrate the feasibility of our approach by successfully running our algorithm on a real mobile robot. The algorithm is novel and unique in that it (a) explores the environment and learns directly on a mobile robot without using a hand-made computer model as an intermediate step, (b) does not require manual discretization of the sensor input space, (c) works in piecewise continuous perceptual spaces, and (d) copes with partial observability. Together this allows learning from much less experience compared to previous methods.
Create a lesson
Related papers
CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators
Kechen Liu, Ola Shorinwa
FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference
Zekai Li, Jiaming Tang, Zhijian Liu
Embodied Scene Rearrangement Planning
Canzhi Chen, Zan Wang, Siqi Zhu et al.
STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaboration
Maitrey Gramopadhye, Prakash Baskaran, Xiao Liu et al.
Tensegrity Continuum Robots Enable Task-Adaptive Morphologies for Cooperative Behaviors
Mahmud Hasan Saikot, Sydney Spiegel, Sudheera Akalanka Kariyawasam et al.
Task-space model-based control of pneumatic soft actuators
Nithin S. Kumar, Joshua Gaston, D. Caleb Rucker et al.