README.md

metadata

tags:
  - CartPole-v1
  - ppo
  - deep-reinforcement-learning
  - reinforcement-learning
  - custom-implementation
  - deep-rl-course
model-index:
  - name: PPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: CartPole-v1
          type: CartPole-v1
        metrics:
          - type: mean_reward
            value: 500.00 +/- 0.00
            name: mean_reward
            verified: false

PPO Agent Playing CartPole-v1

This is a trained model of a PPO agent playing CartPole-v1.

Hyperparameters

{'env_id': 'CartPole-v1'
'seed': 1
'num_envs': 8
'pi_hidden_layers': (64
64)
'v_hidden_layers': (64
64)
'learning_rate': 0.001
'anneal_lr': True
'total_timesteps': 100000
'num_steps': 32
'gamma': 0.98
'gae_lambda': 0.8
'num_minibatches': 1
'num_epochs': 20
'norm_advantage': True
'clip_coef': 0.2
'clip_vloss': True
'vf_coef': 0.5
'ent_coef': 0.0
'max_grad_norm': 0.5
'target_kl': None}