README.md

metadata

tags:
  - LunarLander-v2
  - 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: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - type: mean_reward
            value: '-13.06 +/- 66.33'
            name: mean_reward
            verified: false

PPO Agent Playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2.

Hyperparameters

{'exp_name': 'ppo'
'gym_id': 'LunarLander-v2'
'learning_rate': 0.0003
'seed': 1337
'max_timesteps': 1000000
'torch_deterministic': True
'cuda_enabled': True
'num_envs': 4
'num_steps': 256
'anneal_lr': True
'gae': True
'gae_lambda': 0.95
'gamma': 0.99
'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': 'MakiPan/ppo-CartPole-v1'
'batch_size': 1024
'minibatch_size': 256}