Apprenticeship Learning for a Predictive State Representation of Anesthesia

2020 ◽  
Vol 67 (7) ◽  
pp. 2052-2063 ◽  
Author(s):  
Pierre Humbert ◽  
Clement Dubost ◽  
Julien Audiffren ◽  
Laurent Oudre
Keyword(s):  
State Representation ◽  
Apprenticeship Learning ◽  
Predictive State Representation

scholarly journals Tensor decomposition for multi-agent predictive state representation

2021 ◽  
pp. 115969
Author(s):  
Biyang Ma ◽  
Bilian Chen ◽  
Yifeng Zeng ◽  
Jing Tang ◽  
Langcai Cao
Keyword(s):  
Tensor Decomposition ◽  
State Representation ◽  
Multi Agent ◽  
Predictive State Representation

scholarly journals What is dopamine doing in model-based reinforcement learning?

2020 ◽  
Author(s):  
Thomas Akam ◽  
Mark Walton
Keyword(s):  
Reinforcement Learning ◽  
Prediction Error ◽  
Dopamine Neurons ◽  
State Representation ◽  
Dopaminergic Activity ◽  
Model Based ◽  
Model Free ◽  
Reward Prediction ◽  
Predictive State Representation ◽  
Teaching Signal

Experiments have implicated dopamine in model-based reinforcement learning (RL). These findings are unexpected as dopamine is thought to encode a reward prediction error (RPE), which is the key teaching signal in model-free RL. Here we examine two possible accounts for dopamine’s involvement in model-based RL: the first that dopamine neurons carry a prediction error used to update a type of predictive state representation called a successor representation, the second that two well established aspects of dopaminergic activity, RPEs and surprise signals, can together explain dopamine’s involvement in model-based RL.

scholarly journals Low Dimensional State Representation Learning with Reward-shaped Priors

2021 ◽  
Author(s):  
Nicolo Botteghi ◽  
Ruben Obbink ◽  
Daan Geijs ◽  
Mannes Poel ◽  
Beril Sirmacek ◽  
...  
Keyword(s):  
Representation Learning ◽  
State Representation ◽  
Low Dimensional

APPLICATION OF ENTANGLED STATE IN QUANTIZING SUPERCONDUCTING CAPACITOR MODEL IN THE PRESENCE OF A VOLTAGE BIAS AND A CURRENT BIAS

2004 ◽  
Vol 18 (02) ◽  
pp. 233-240 ◽  
Author(s):  
HONG-YI FAN
Keyword(s):  
Operator Theory ◽  
Hamiltonian Operator ◽  
Entangled State ◽  
Entangled State Representation ◽  
Phase Operator ◽  
State Representation ◽  
Voltage Bias ◽  
A Current

Based on the entangled state representation and the appropriate bosonic phase operator we develop the superconducting capacitor model in the presence of a voltage bias and a current bias. In so doing, the full Hamiltonian operator theory for a superconducting barrier is established.

Sign in / Sign up

Export Citation Format

Share Document