suveda999/ppo-LunarLander-v3-cleanrl

PPO Agent Playing LunarLander-v3

This is a trained model of a PPO agent playing LunarLander-v3.

Hyperparameters

• exp_name: ppo
• seed: 1
• torch_deterministic: True
• cuda: True
• env_id: LunarLander-v3
• total_timesteps: 1000000
• learning_rate: 0.0003
• num_envs: 16
• num_steps: 256
• anneal_lr: True
• gae: True
• gamma: 0.999
• gae_lambda: 0.98
• num_minibatches: 16
• 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: suveda999/ppo-LunarLander-v3-cleanrl
• batch_size: 4096
• minibatch_size: 256