The document discusses reinforcement learning concepts like states, actions, rewards, and how reinforcement learning agents can learn optimal policies through trial-and-error interactions with an environment by maximizing rewards. It uses the example of learning to play the card game Exploding Kittens through reinforcement learning by receiving different rewards for drawing certain cards and learning which moves maximize long term rewards. The document also contrasts reinforcement learning with supervised learning and other machine learning techniques.
2. Why Reinforcement Learning?
I learned after
playing many times;
That I‘m more likely to
win if I played this move
after that one.
No one kept telling me
make this or that move!
10. Deep Q Learning
State Feature1 State Feature2 Action Value
10 20 JUMP 0.5
20 15 DUCK 0.6
15 25 JUMP 0.8
Warning:Over simplification Ahead
This is a Q-Table;
What if there are too many States & Actions?
11. MDP, MC and TD
Markov Decision Process:
● You need to know the states and the transitions between them.
Monte Carlo (variance ↑):
● You wait till episode’s end, and re-assign values to states.
● No need to even know the states, we sample from the environment.
Temporal Difference (bias ↑):
● Update on the go. No need to even have goal states.
12. Let’s play the RL vs SL game
for (i=0; i<3; i++) {
● Pick a catawiki problem
● Should it be solved via
○ Reinforcement learning?
○ Supervised learning?
}
Hinweis der Redaktion
We expect, in general, that the environment will be nondeterministic; that is, that taking the same action in the same state on two different occasions may result in different next states and/or different reinforcement values. However, we assume the environment is stationary; that is, that the probabilities of making state transitions or receiving specific reinforcement signals do not change over time.
Reinforcement learning differs from the more widely studied problem of supervised learning in several ways. The most important difference is that there is no presentation of input/output pairs. Instead, after choosing an action the agent is told the immediate reward and the subsequent state, but is not told which action would have been in its best long-term interests. It is necessary for the agent to gather useful experience about the possible system states, actions, transitions and rewards actively to act optimally.
Another difference from supervised learning is that on-line performance is important: the evaluation of the system is often concurrent with learning.
Use cases for RL: if there is path dependence (i.e. the order of your moves matter, like in chess), if you have a budget (e.g. max # emails to send, money), or if your decisions select your future training examples (e.g. (greedily) not bidding on new websites in programmatic advertising will never allow you acquire data about them). (via Peter Tegelaar)