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: 112.20 +/- 67.63
            name: mean_reward
            verified: false

PPO Agent Playing CartPole-v1

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

Hyperparameters

{'exp_name': 'ppo-11'
'gym_id': 'CartPole-v1'
'env_id': 'CartPole-v1'
'learning_rate': 0.00025
'seed': 1
'total_timesteps': 25000
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'ppo-implementation-details'
'wandb_entity': None
'capture_video': False
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'juanzinser/ppo-CartPole-v1'
'batch_size': 512
'minibatch_size': 128}