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: '-30.85 +/- 140.48'
            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': 'debug'
'gym_id': 'LunarLander-v2'
'hface_repo': 'EExe/my_ppo_LunarLand'
'learning_rate': 0.00025
'seed': 42
'total_timesteps': 2000000
'num_envs': 4
'num_steps': 1024
'gamma': 0.999
'gae_lambda': 0.98
'num_minibatches': 64
'num_epochs': 10
'clip_coeff': 0.2
'ent_coeff': 0.1
'vf_coeff': 0.1
'max_gradient_norm': 0.5
'target_kl': 0.015}