Sumários

Reinforcement learning exercise

19 Abril 2021, 18:30 Luís Miguel Parreira e Correia

Programming stochastic reinforcement learning and epsilon-greedy algorithm


Reiforcement learning

19 Abril 2021, 16:30 Luís Miguel Parreira e Correia

Reinforcement learning; dynamic programming; Q-learning; Stochastic Q-learning


Exercise with TLFN

12 Abril 2021, 18:30 Helena Aidos

Experiments wit time lagged feefforward network for time series forecast.


Exercise with TLFN

12 Abril 2021, 18:30 Luís Miguel Parreira e Correia

Experiments wit time lagged feefforward network for time series forecast.


Filtering in time series learning

12 Abril 2021, 16:30 Luís Miguel Parreira e Correia

Unit delay filters; Time lagged feedforward networks