1. at time \(t\), agent received observation \(o_{t}\)
2. agent then chooses \(a_{t}\) based on what it knows through some kind of process in order to affect a possibly nondeterministic change on the environment
   • the agent choose an \(a_{t}\) under the existance of many types of Uncertainty.

\begin{equation} V = IR \end{equation}

where, \(V\) is the voltage across the resister, \(I\) the current, and \(R\) the resistance.

power (physics)

the rate at which electrical energy dissipates into heat is called power:

\begin{equation} P = IV \end{equation}

where, \(P\) is power, and \(I\) the current, and \(V\) the voltage.

Alternate formulation of power:

\begin{equation} P = I V = \frac{V^{2}}{R} = I^{2} R = \dv{E}{t} \end{equation}

Transformers has replaced large pipelines into a single system.

“Transformers verticalized tasks in 2013 EMNLP; various domains”

Process

1. Multiple manual systems that talk to each other has been replaced by neurons talking to each other
2. General word embeddings like Word2Vec
3. Sequence to sequence modeling from those vecs that are more general: learning variable length representations
4. From LSTMs to Encoder-Decoder architectures: Google Neural Machine Translation System 2016 (LSTM seq2seq SoTA)

So: big complicated pipelines turn into one homogeneous system.

Everyday, at 11:00 PM exactly, I stop time tracking.

And it feels somehow as the most liberating time of my day. When I truly feels like I have my time back to myself,