A classical agent extracts more work from quantum temporal correlations via adaptive strategies bounded by the new Time-Ordered Free Energy, while reinforcement learning achieves polylogarithmic dissipation when learning unknown states.
On the use of non-stationary policies for stationary infinite-horizon markov decision processes.Advances in Neural Information Processing Systems, 25, 2012
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
quant-ph 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Demon that remembers: An agential approach towards quantum thermodynamics of temporal correlations
A classical agent extracts more work from quantum temporal correlations via adaptive strategies bounded by the new Time-Ordered Free Energy, while reinforcement learning achieves polylogarithmic dissipation when learning unknown states.