micdestefano
/

Reinforce-Cartpole-v1

Reinforcement Learning

custom-implementation

Model card Files Files and versions Community

Jarlaxle commited on Dec 16, 2023

Commit

766f9ab

·

1 Parent(s): 1d6b651

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -26,4 +26,6 @@ model-index:
   To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
   Some notes: I used gymnasium and not gym, so I had to modify some instructions to make the page work. I trained the agent for 2000 episodes and I achieved a model that never makes the pole fall!!!

   To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
   Some notes: I used gymnasium and not gym, so I had to modify some instructions to make the page work. I trained the agent for 2000 episodes and I achieved a model that never makes the pole fall!!!
+  The final score is 100000 only because I let the scoring function evaluate a maximum of 100000 steps ... but the score could be +infinity if I let the game going on forever!!!