AI Learns to Play Street Fighter and Mortal Kombat (reinforcement learning)

Channel:
Subscribers:
1,350
Published on ● Video Link: https://www.youtube.com/watch?v=Rzz0MfgsHOI



Duration: 6:57
4 views
0


Proximal Policy Optimization (PPO) is a more advanced type of reinforcement learning algorithm developed by Schulman et al. It's used to train an agent to play many of the games, though it takes a while and is much faster with a GPU. The Brute is a simple but effective reinforcement learning algorithm that works on deterministic environments like Gym Retro games.

Watch an epic clash between PPO and The Brute in classic fighting games. Who will emerge victorious?

The Brute: https://arxiv.org/pdf/1709.06009.pdf
PPO: https://arxiv.org/pdf/1707.06347.pdf

Link 1 (SF Figures. 30% off): https://s.click.aliexpress.com/e/_mPwuNyW
Link 2 (MK Pendant . 42% off): https://s.click.aliexpress.com/e/_okIqFNW
Link 3 (Shao Khan): https://amzn.to/3UhesGS
Link 4 (Sonya Blade): https://amzn.to/3vP1BBo
Link 5 (CAMMY Figures): https://amzn.to/47Ucq2e

News? https://bit.ly/play-screen







Tags:
proximal policy optimization
proximal policy optimization algorithms
proximal policy optimization algorithm
proximal policy optimization ppo
proximal policy optimization explained
what is proximal policy optimization
machine learning
ppo
proximal policy optimization python
brute force the algorithm
the brute force algorithm
the algorithm brute force
deep learning
reinforcement learning
deep reinforcement learning
Street Fighter
Mortal Kombat