{ "exp_name": "ppo_cleanrl_colab", "seed": 1, "torch_deterministic": true, "cuda": true, "capture_video": false, "env_id": "CartPole-v1", "total_timesteps": 20000, "learning_rate": 0.00025, "num_envs": 4, "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": null, "repo_id": "joshkaura/ppo-CartPole-v1", "batch_size": 512, "minibatch_size": 128 }