New answers tagged q-learning
2
votes
Accepted
How do I create an AI controller for Pacman?
About the environments
For the controller part of your question, I would advice looking at openAI gym.
https://www.gymlibrary.ml/content/environment_creation/ #how to make your own gym enviroment
...
1
vote
Accepted
How to compare memory requirements for tabular Q-learning vs deep neural network?
You don't say, but I suspect from your description, that you have designed the neural network to operate over one-hot-encoding representations of states and actions. Using such a representation offers ...
1
vote
Is the described Q-table considered large?
There a couple of "rules of thumb" you might apply to decide whether a Q table is large enough that some kind of approximation would help:
Does it fit into memory?
Does the rate of ...
0
votes
Accepted
Is it possible to add states to the Q-table after the game has started?
Yes, it is possible to add states to a Q table after the game has started, for example by storing the "table" in a binary tree.
Nonetheless, with a simple interpretation of state (like all ...
1
vote
Accepted
How to deal with changing rewards in Q-learning? DQN?
Is my definition of 'state' or 'action' wrong?
I hesitate to say 'wrong', but that's not how state and action are defined in RL, and that mismatch might make the algorithms hard to understand.
In RL ...
Top 50 recent answers are included
Related Tags
q-learning × 342reinforcement-learning × 300
dqn × 100
deep-rl × 74
deep-learning × 33
machine-learning × 27
neural-networks × 23
sarsa × 18
markov-decision-process × 17
convergence × 17
value-functions × 16
comparison × 13
python × 12
game-ai × 11
state-spaces × 11
experience-replay × 10
papers × 9
off-policy-methods × 9
exploration-exploitation-tradeoff × 9
training × 8
ai-design × 8
rewards × 8
open-ai × 8
function-approximation × 8
gym × 8