Papers
4
Total Citations
154
H-Index
4
About
Massimiliano Schembri is a researcher whose work sits at the intersection of robotics, machine learning, and artificial intelligence, with a particular focus on intrinsically motivated reinforcement learning (IMRL) and autonomous skill acquisition. His most influential contributions, concentrated in a productive 2007 period, address a fundamental challenge in robotics: enabling agents to develop reusable, general-purpose behavioral skills that can be flexibly combined to solve diverse tasks without requiring explicit external reward for every objective. Schembri's most cited work, "Evolving Internal Reinforcers for an Intrinsically Motivated Reinforcement Learning Robot" (78 citations), advanced the theoretical and architectural foundations of IMRL by demonstrating how evolutionary mechanisms can shape the internal reward signals that drive a robot's curiosity-like learning. Complementary papers explored how childhood length and learning parameters themselves could be evolved, revealing that developmental timing profoundly influences the quality of skills a robot acquires. Collectively, these contributions helped establish a biologically inspired paradigm for open-ended robot learning. Later work applying artificial life principles to serious game design reflects a broader interest in adaptive, lifelike systems. With over 150 cumulative citations, Schembri's research has meaningfully influenced discussions on autonomous learning, developmental robotics, and the design of self-motivated artificial agents.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4