shash0609/ppo-LunarLander-v2

PPO Agent Playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2 (trained using Gymnasium LunarLander-v3).

Hyperparameters

exp_name: ppo_lunar_lander_v3
seed: 1
torch_deterministic: True
cuda: False
track: False
wandb_project_name: cleanRL
wandb_entity: None
capture_video: False
env_id: LunarLander-v3
hub_env_id: LunarLander-v2
total_timesteps: 300000
learning_rate: 0.00025
num_envs: 8
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: shash0609/ppo-LunarLander-v2
batch_size: 1024
minibatch_size: 256