hidden_sizes: [128, 128]
total_timesteps: 1000000
rollout_steps: 1024
learning_epochs: 4
mini_batches: 4
discount_factor: 0.99
gae_lambda: 0.95
learning_rate: 0.0003
clip_ratio: 0.2
value_loss_scale: 0.5
entropy_loss_scale: 0.01
log_interval: 10
clearml_project: RL-Framework