OGC/src/config/configs/overcooked/baseline_dr_s55x5.json
2024-06-25 16:22:33 +02:00

68 lines
No EOL
2.4 KiB
JSON

{
"args": {
"seed": [1],
"agent_rl_algo": ["ppo"],
"n_total_updates": [30000],
"train_runner": ["dr"],
"n_devices": [1],
"student_model_name": ["default_student_actor_cnn"],
"student_critic_model_name": ["default_student_critic_cnn"],
"env_name": ["Overcooked"],
"is_multi_agent": [true],
"verbose": [false],
"log_dir": ["~/logs/minimax"],
"log_interval": [10],
"from_last_checkpoint": [false],
"checkpoint_interval": [1000],
"archive_interval": [0],
"archive_init_checkpoint": [false],
"test_interval": [100],
"n_students": [1],
"n_parallel": [32],
"n_eval": [1],
"n_rollout_steps": [400],
"lr": [3e-4],
"lr_anneal_steps": [0],
"max_grad_norm": [0.5],
"adam_eps": [1e-05],
"track_env_metrics": [true],
"discount": [0.999],
"n_unroll_rollout": [10],
"render": [false],
"student_gae_lambda": [0.98],
"student_entropy_coef": [0.01],
"student_value_loss_coef": [0.5],
"student_n_unroll_update": [5],
"student_ppo_n_epochs": [8],
"student_ppo_n_minibatches": [4],
"student_ppo_clip_eps": [0.2],
"student_ppo_clip_value_loss": [true],
"student_recurrent_arch": ["s5"],
"student_recurrent_hidden_dim": [64],
"student_hidden_dim": [64],
"student_n_hidden_layers": [3],
"student_n_conv_layers": [3],
"student_n_conv_filters": [32],
"student_n_scalar_embeddings": [4],
"student_scalar_embed_dim": [5],
"student_s5_n_blocks": [2],
"student_s5_n_layers": [2],
"student_s5_layernorm_pos": ["pre"],
"student_s5_activation": ["half_glu1"],
"student_agent_kind": ["mappo"],
"overcooked_height": [5],
"overcooked_width": [5],
"overcooked_n_walls": [15],
"overcooked_replace_wall_pos": [true],
"overcooked_sample_n_walls": [true],
"overcooked_normalize_obs": [true],
"overcooked_max_steps": [400],
"overcooked_random_reset": [false],
"n_shaped_reward_updates": [30000],
"test_n_episodes": [10],
"test_env_names": [
"Overcooked-CoordRing5_5,Overcooked-ForcedCoord5_5,Overcooked-CrampedRoom5_5"
],
"overcooked_test_normalize_obs": [true]
}
}