hyperparams.json

{
  "batch_size": 64,
  "clip_range": 0.2,
  "device": "cpu",
  "ent_coef": 0.0,
  "gae_lambda": 0.95,
  "gamma": 0.99,
  "learning_rate": 0.0003,
  "max_grad_norm": 0.5,
  "n_steps": 2048,
  "policy": "ActorCriticPolicy",
  "vf_coef": 0.5
}