Local Optimum Breakouts in Reinforcement Learning and Supervised Learning

July 4, 2023•26 words

Reinforcement learning reward sum diagram has breakout points from current local optima, as shown below:

Similarly, in supervised learning, the loss curve has local optimum breakout points too:

👍❤️🫶👏👌🤯🤔😂😍😭😢😡😮

Subscribe to the author

You'll only receive email when they publish something new.

More from 19411
All posts

The Most Basic Toy Problems for Neural Network

July 4, 2023•176 words

The most and top most basic one: A+B=? Solution: A single neuron, 2 weights, 1 bias, identity activation Training result: The 2 weights reach 1, bias goes zero Other basic toy problems: AND,OR: A single neuron can solve, 1 separation line XOR: A single layer of 2 neurons can solve with 2 separation lines, but it needs a single-value output, so put it 2 layers of 2 neurons then 1 neuron respectively. Theory notes: 1 neuron makes 1 separation line 1 layer makes 1 separation...

Read post

Q-network vs Policy Network in Reinforcement Learning

July 4, 2023•238 words

Q-network (aka Deep Q-network) Input: State (Env+Agent), Action Output: Single neuron Q-value (current reward and future return) Characteristics: Find max action and train to that label=q(s,a) Closely linked with Q-learning concept Explore: Random Exploit: Use q-network at current moment to exploit for max action through max q-value Training: Bellman target q-value Update q-value 1 by 1, q = r + max(q[t+1]) Policy Network (applicable to fixed number of actions ...

Read post

Local Optimum Breakouts in Reinforcement Learning and Supervised Learning

More from 19411All posts

The Most Basic Toy Problems for Neural Network

Q-network vs Policy Network in Reinforcement Learning

More from 19411
All posts