OpenAI Gym: ceobillionaire’s algorithm on Humanoid-v1

OpenAI Gym : Training an Agent to make a Humanoid walk fast! 
#AI #DeepLearning #RL

  • (Humanoid-v1 does not have a specified reward threshold at which it’s considered solved.)
  • Nav
  • Best 100-episode average reward was 9606.88 ± 53.68.

Read the full article, click here.


@ceobillionaire: “OpenAI Gym : Training an Agent to make a Humanoid walk fast!
#AI #DeepLearning #RL”



OpenAI Gym: ceobillionaire’s algorithm on Humanoid-v1