Exploring Deep Q Learning Agent Progression Lunarlander V2
Exploring Deep Q Learning Agent Progression Lunarlander V2 reveals several interesting facts.
- Like & Subscribe.
- This video shows the results obtained by using a DQN
- Landing pad is always at coordinates (0,0). Coordinates are the first two numbers in state vector. Reward for moving from the top ...
- Deep Q Learning
- Useful Videos - Local Network vs Target Network - https://youtu.be/FhGq_GNicIM Exploration-Exploitation Tradeoff ...
In-Depth Information on Deep Q Learning Agent Progression Lunarlander V2
This is a video recording the Deep neural networks design of RL agents for Lunar-Lander in openAI gym Python and Pytorch. Solved with
Lecture
Stay tuned for more updates related to Deep Q Learning Agent Progression Lunarlander V2.
