metadata
tags:
- CartPole-v1
- ppo
- cleanrl
- reinforcement-learning
- deep-rl-class
- custom-implementation
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 83.60 +/- 50.09
name: mean_reward
verified: false
PPO Agent Playing CartPole-v1
Trained with a minimal CleanRL-style PPO implementation in Google Colab.
Results
- Mean reward: 83.60
- Std reward: 50.09