Deep Learning

Deep RL

Reinforcement learning where the policy is a deep network.

Combining reinforcement learning with deep networks let agents learn control directly from raw input such as pixels, rather than from hand-engineered state descriptions.

It is powerful and notoriously fragile: sample-hungry, sensitive to seeds and hyperparameters, and prone to exploiting flaws in a reward function rather than solving the intended task.

Also in Deep Learning

CNN RNN LSTM Transformers Auto Encoders Epochs

JOIN NOW

Begin the first module

It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.

See the curriculum

Join any time · Build AI skills at your pace