itsChibi
Reputation: 71
Defining state and action for Q-learning in the code
I am trying to understand the following code for the simulator to avoid collision with the help of Q-learning. The examples and tutorials which I followed had the space divided into blocks such as taxiv3, so it was rather easier to define state and action spaces. But in this code, the simulator produces random sectors and I am trying to figure out a way to define the state space and action space.
Please let me know if you need more information on my question if it is too vague.
https://github.com/ramondalmau/atcenv/blob/main/atcenv/env.py
Upvotes: 1
Views: 21
Answers (0)
Related Questions
- Deep reinforcement learning - how to deal with boundaries in action space
- Deep Q Learning - Cartpole Environment
- DQN understanding input and output (layer)
- Input states for Deep Q Learning
- Setting up target values for Deep Q-Learning
- How can I apply reinforcement learning to continuous action spaces?
- Why and when is deep reinforcement learning needed instead of q-learning?
- Initialization state in DQN
- Q-Learning equation in Deep Q Network
- Q-learning: What is the correct state for reward calculation