rondahahda/ppo-scratch-LunarLander-v2

PPO Agent Playing LunarLander-v2

A PPO agent written from scratch (CleanRL style) for the Hugging Face Deep RL Course, Unit 8 part 1.

Hyperparameters

{
  "env_id": "LunarLander-v2",
  "seed": 1,
  "total_timesteps": 1000000,
  "learning_rate": 0.00025,
  "num_envs": 8,
  "num_steps": 256,
  "gamma": 0.99,
  "gae_lambda": 0.95,
  "num_minibatches": 4,
  "update_epochs": 4,
  "clip_coef": 0.2,
  "ent_coef": 0.01,
  "vf_coef": 0.5,
  "max_grad_norm": 0.5
}