Exploring Lunarlander V2
Let's dive into the details surrounding Lunarlander V2.
- Showcasing an agent trained with DQN on the
- Double DQN algorithm which is applied to
- DQN Baseline hyperaparameters. DQN hyperparameters tuned by CMA-ES.
- Timecodes: 0:00 Introduction 0:25 Code overview 1:08 Solution explanation 5:52 Conclusion.
- This is a trained AI built using the OpenAI Gym LunarLander_v2 environment. The AI achieves a reward score of over 300 ...
In-Depth Information on Lunarlander V2
Reinforcement Learning (vanilla policy gradients) to land on the Moon. OpenAI Gym's 3 layer Neural Network that learned to land space craft on surface with reduced fuel consumption through reinforcement learning ... Like & Subscribe.
Luner Lander Result after training.
That wraps up our extensive overview of Lunarlander V2.