1.

Turing machine
- hypothetical machine that represents a computing machine
- Turing machines mathematically model a device that mechanically runs using a tape.
This tape includes symbols, which the machine can write and read, one after the
other, with the help of a tape head.
- [Tape, Head, State Register, Finite Table]
o A tape that is split into cells, one beside the other. Every cell includes a symbol from a certain
finite alphabet. The alphabet includes a unique blank symbol as well as one or more other
symbols. The volume of tape required for the computation is always included in the Turing
machine.
o A head that is able to write and read symbols on the tape. In certain models, the head moves
while the tape is fixed.
o A state register to store the Turing machine's state. There is a special start state through
which the state register is initialized.
o A finite table (sometimes referred to as a transition function or an action table) of
instructions, which are generally quintuples, but occasionally quadruples.

2. Previous versions of AlphaGo initially trained on thousands of human amateur and

professional games to learn how to play Go. AlphaGo Zero skips this step and learns
to play simply by playing games against itself, starting from completely random
play. In doing so, it quickly surpassed human level of play and defeated the previously
published champion-defeating version of AlphaGo by 100 games to 0.
It is able to do this by using a novel form of reinforcement learning, in which AlphaGo
Zero becomes its own teacher. The system starts off with a neural network that knows
nothing about the game of Go. It then plays games against itself, by combining this
neural network with a powerful search algorithm. As it plays, the neural network is
tuned and updated to predict moves, as well as the eventual winner of the games.

3. PLANNING
(how an agent can take advantage of the structure of a problem to construct complex plans of action)
- Planning – devising a plan of action to achieve one's goals