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: 35.48 +/- 126.92
            name: mean_reward
            verified: false

PPO Agent Playing LunarLander-v2

A PPO agent playing LunarLander-v2 but decides to go for a walk instead.

Do not download it if you are looking for an agent that follows the plan.

Hyperparameters

{"exp_name": "ppo"
"seed": 1
"torch_deterministic": true
"cuda": true
"track": false
"wandb_project_name": "cleanRL"
"wandb_entity": null
"capture_video": false
"env_id": "LunarLander-v2"
"total_timesteps": 1000000
"learning_rate": 0.00025
"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": null
"repo_id": "salym/PPO-CleanRL-LunarLander-v2"
"batch_size": 512
"minibatch_size": 128}