441 questions
Advice
0
votes
0
replies
60
views
Please explain this vectorized Bellman's Equation
Can some please explain this vectorized Bellman equation to me in simple terms?
The Bellman equation usually has "summation symbol", "summation symbol", "summation symbol"...
0
votes
1
answer
67
views
Why does the CityLearn tutorial keep throwing me a ValueError?
I am following this CityLearn tutorial.
I got through the first part (RBC) without incident. However, when I implement the second part (Q-learning, literally copy and paste from the site), I keep ...
-1
votes
1
answer
44
views
DQN performance swinging
I'm using DDQN with experience replay just like in this tutorial https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html
except that I'm making the problem a little harder by ...
- 51
1
vote
0
answers
44
views
How to incorporate energy consumption into the reward function in Q-learning for robot navigation in a flow field?
I'm working on a Q-learning implementation to help a robot navigate within a double gyre flow field. The objective is to find an optimal path between two points in the flow while minimizing energy ...
- 11
0
votes
1
answer
99
views
reinforcement learning reward choices
To start with, this is not a homework thing. In my attempt to finally get a practical working knowledge of table based re-inforcement learning, I came up with a very silly and easy dice game, serving ...
- 12.2k
0
votes
1
answer
78
views
Why do I get different testing result using the same Q-value table
I am studying ML and was trying to make a reinforcement learning algorithm for a gymnasium environment. I already made a q-learning for a very basic and simple problem and I decided to use the same ...
- 11
-2
votes
1
answer
73
views
How can i proceed further in this AI/ML project? [closed]
I have 10 datasets (.csv) each with 100,000 rows, with each row containing 5 inputs ( -4.0f to +4.0f) and a output column (0/1). I want to train a Neural Network using this and predict the test ...
1
vote
0
answers
57
views
How to Implement 'game rules' when training a Deep Q Network
I am trying to make a Deep-Q-network that teaches itself to play modified versions of tictactoe (a m,n,k-game)
I want to make sure the network does not place a mark where there already is a mark
I ...
- 11
1
vote
0
answers
121
views
What kind of reward should I set in q-learning to get values closer to the result I expect?
I'm working on a Q-learning project using OpenAI Gym and PyBullet drones. My goal is to control the height of the drone so that it stays at a height of 1 and remains stable at that point. I'm using ...
- 21
2
votes
1
answer
70
views
Haskell GriWorld Infinite loop
I'm trying to code a GridWorld simulation in Haskell via reinforcement learning. I'm stuck because I keep falling into an infinite loop on line 109. I've been staring at this problem for a week, and I ...
- 33
2
votes
1
answer
932
views
Does initializing a Q-table with zeros introduce bias towards the first action in reinforcement learning? [closed]
I'm working on a reinforcement learning problem where I've initialised the Q-table with zeros. I noticed that when all Q-values for different actions are initially set to zero, the arg-max function ...
- 29
1
vote
1
answer
62
views
Qtable index out of bounds
Im trying to make a simple Q-learning AI in gms2, but im horrible messing with grinds and aways get the same problem when i try to update the qTable:
index out of bounds
project is simple, the AI can ...
- 11
0
votes
1
answer
148
views
flappy bird linear q leanring approximation don't learn
Before asking for help, I apologize for my English. I'm from Switzerland, so it is not my first language. I am currently building a reinforcement learning bot to learn how to play Flappy Bird. I am ...
- 21
0
votes
1
answer
192
views
Q Learning agent taking too many steps to reach goal
I'm currently working on implementing Q-learning for the FrozenLake-v1 environment in OpenAI Gym. However, my agent seems to like taking a lot of unnecessary steps to get to the goal. I've reviewed my ...
- 50
0
votes
1
answer
196
views
Python Gymnasium Render being forced
I'm new to gym and I tried to do a simple qlearning programm but for some (weird) reason it won't let me get rid of the rendering part (which is taking forever)...
Here is my programm:
import ...
- 1