SimingSiming's picture
Update README.md
b975a7f
metadata
tags:
  - CartPole-v1
  - reinforce
  - reinforcement-learning
  - custom-implementation
  - deep-rl-class
model-index:
  - name: reinforce-CartPole-v2
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: CartPole-v1
          type: CartPole-v1
        metrics:
          - type: mean_reward
            value: 221.40 +/- 16.12
            name: mean_reward
            verified: false

parameters

cartpole_hyperparameters = {
"h_size": 16,
"n_training_episodes": 1000,
"n_evaluation_episodes": 10,
"max_t": 1000,
"gamma": 1.0,
"lr": 1e-2,
"env_id": env_id,
"state_space": s_size,
"action_space": a_size,
}