Projective simulation with generalization

Abstract

The ability to generalize is an important feature of any intelligent agent. Not only because it may allow the agent to cope with large amounts of data, but also because in some environments, an agent with no generalization capabilities cannot learn. In this work we outline several criteria for generalization, and present a dynamic and autonomous machinery that enables projective simulation agents to meaningfully generalize. Projective simulation, a novel, physical approach to artificial intelligence, was recently shown to perform well in standard reinforcement learning problems, with applications in advanced robotics as well as quantum experiments. Both the basic projective simulation model and the presented generalization machinery are based on very simple principles. This allows us to provide a full analytical analysis of the agent's performance and to illustrate the benefit the agent gains by generalizing. Specifically, we show that already in basic (but extreme) environments, learning without generalization may be impossible, and demonstrate how the presented generalization machinery enables the projective simulation agent to learn.

14 pages, 9 figures

References in corpus (8)

• Exponential algorithmic speedup by quantum walk
• Quantum-enhanced machine learning
• Active learning machine learns to create new quantum experiments
• Coherent controlization using superconducting qubits
• Meta-learning within Projective Simulation
• Quantum-enhanced deliberation of learning agents using trapped ions
• Speeding-up the decision making of a learning agent using an ion trap quantum processor
• Robotic Playing for Hierarchical Complex Skill Learning

Cited by in corpus (24)

• Active learning machine learns to create new quantum experiments
• Optimizing Quantum Error Correction Codes with Reinforcement Learning
• Machine learning for long-distance quantum communication
• Quantum Machine Learning: from physics to software engineering
• Measurement-based adaptation protocol with quantum reinforcement learning
• Quantum classification of the MNIST dataset with Slow Feature Analysis
• Machine learning \& artificial intelligence in the quantum domain
• Setting up experimental Bell test with reinforcement learning
• Meta-learning within Projective Simulation
• Modelling collective motion based on the principle of agency
• Speeding-up the decision making of a learning agent using an ion trap quantum processor
• Photonic architecture for reinforcement learning
• Operationally meaningful representations of physical systems in neural networks
• Benchmarking projective simulation in navigation problems
• Development of swarm behavior in artificial learning agents that adapt to different foraging environments
• Quantum reinforcement learning in continuous action space
• On the convergence of projective-simulation-based reinforcement learning in Markov decision processes
• Skill Learning by Autonomous Robotic Playing using Active Learning and Creativity
• Quantum machine learning with glow for episodic tasks and decision games
• Hybrid discrete-continuous compilation of trapped-ion quantum circuits with deep reinforcement learning
• Optimal foraging strategies can be learned
• Can biological quantum networks solve NP-hard problems?
• Unitary Evolutions Sourced By Interacting Quantum Memories: Closed Quantum Systems Directing Themselves Using Their State Histories
• A Projective Simulation Scheme for Partially-Observable Multi-Agent Systems