A live coding session on the IBM Developer Twitch channel showing how to use and train a Reinforcement Learning algorithm to play a simple game.
OpenAI Gym is an API that allows you to easily interface reinforcement learning "environments" (that describe the problem) to "agents" (that attempt to learn to solve the problem. This allows you to define your problem and then use existing state-of-the-art RL agents to train on it.
https://cinnamon.video/watch?v=405086919685310352
OpenAI Gym is an API that allows you to easily interface reinforcement learning "environments" (that describe the problem) to "agents" (that attempt to learn to solve the problem. This allows you to define your problem and then use existing state-of-the-art RL agents to train on it.
https://cinnamon.video/watch?v=405086919685310352