| environment: LunarLander-v3 | |
| algorithm: PPO | |
| seed: 1 | |
| total_timesteps: 100000 | |
| 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_advantage: True | |
| clip_coefficient: 0.2 | |
| clip_value_loss: True | |
| entropy_coefficient: 0.01 | |
| value_function_coefficient: 0.5 | |
| max_grad_norm: 0.5 | |