Quantum machine learning with glow for episodic tasks and decision games
This work proposes a quantum-enhanced reinforcement learning approach for episodic tasks, but it appears incremental as it adapts existing projective simulation methods to a quantum framework without demonstrating clear superiority over classical baselines.
The authors tackled the problem of reinforcement learning in episodic tasks and decision games by developing a quantum machine learning agent that encodes perceptual inputs as quantum states and updates its memory via a quantum channel with a glow mechanism, achieving performance comparable to a basic classical projective simulation agent in invasion games and grid worlds.
We consider a general class of models, where a reinforcement learning (RL) agent learns from cyclic interactions with an external environment via classical signals. Perceptual inputs are encoded as quantum states, which are subsequently transformed by a quantum channel representing the agent's memory, while the outcomes of measurements performed at the channel's output determine the agent's actions. The learning takes place via stepwise modifications of the channel properties. They are described by an update rule that is inspired by the projective simulation (PS) model and equipped with a glow mechanism that allows for a backpropagation of policy changes, analogous to the eligibility traces in RL and edge glow in PS. In this way, the model combines features of PS with the ability for generalization, offered by its physical embodiment as a quantum system. We apply the agent to various setups of an invasion game and a grid world, which serve as elementary model tasks allowing a direct comparison with a basic classical PS agent.