| { |
| "help": false, |
| "algo": "APPO", |
| "env": "GDY-PowerGrid", |
| "experiment": "p2.fa.clean", |
| "train_dir": "/workspace/metta/train_dir", |
| "restart_behavior": "resume", |
| "device": "gpu", |
| "seed": null, |
| "num_policies": 1, |
| "async_rl": true, |
| "serial_mode": false, |
| "batched_sampling": false, |
| "num_batches_to_accumulate": 2, |
| "worker_num_splits": 2, |
| "policy_workers_per_policy": 1, |
| "max_policy_lag": 50, |
| "num_workers": 32, |
| "num_envs_per_worker": 2, |
| "batch_size": 16384, |
| "num_batches_per_epoch": 1, |
| "num_epochs": 1, |
| "rollout": 256, |
| "recurrence": 256, |
| "shuffle_minibatches": false, |
| "gamma": 0.99, |
| "reward_scale": 1.0, |
| "reward_clip": 1000.0, |
| "value_bootstrap": false, |
| "normalize_returns": true, |
| "exploration_loss_coeff": 0.002, |
| "value_loss_coeff": 0.976, |
| "kl_loss_coeff": 0.0, |
| "aux_loss_coeff": 0.0, |
| "exploration_loss": "symmetric_kl", |
| "gae_lambda": 0.95, |
| "ppo_clip_ratio": 0.1, |
| "ppo_clip_value": 1.0, |
| "with_vtrace": false, |
| "vtrace_rho": 1.0, |
| "vtrace_c": 1.0, |
| "optimizer": "adam", |
| "adam_eps": 1e-06, |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.999, |
| "max_grad_norm": 4.0, |
| "learning_rate": 0.0001, |
| "lr_schedule": "constant", |
| "lr_schedule_kl_threshold": 0.008, |
| "lr_adaptive_min": 1e-06, |
| "lr_adaptive_max": 0.01, |
| "obs_subtract_mean": 0.0, |
| "obs_scale": 1.0, |
| "normalize_input": false, |
| "normalize_input_keys": null, |
| "decorrelate_experience_max_seconds": 150, |
| "decorrelate_envs_on_one_worker": true, |
| "actor_worker_gpus": [], |
| "set_workers_cpu_affinity": true, |
| "force_envs_single_thread": false, |
| "default_niceness": 0, |
| "log_to_file": true, |
| "experiment_summaries_interval": 10, |
| "flush_summaries_interval": 30, |
| "stats_avg": 100, |
| "summaries_use_frameskip": true, |
| "heartbeat_interval": 20, |
| "heartbeat_reporting_interval": 180, |
| "train_for_env_steps": 9999999999999, |
| "train_for_seconds": 10000000000, |
| "save_every_sec": 120, |
| "keep_checkpoints": 2, |
| "load_checkpoint_path": null, |
| "init_checkpoint_path": null, |
| "load_checkpoint_kind": "latest", |
| "save_milestones_sec": -1, |
| "save_best_every_sec": 5, |
| "save_best_metric": "reward", |
| "save_best_after": 100000, |
| "benchmark": false, |
| "encoder_mlp_layers": [ |
| 512, |
| 512 |
| ], |
| "encoder_conv_architecture": "convnet_simple", |
| "encoder_conv_mlp_layers": [ |
| 512 |
| ], |
| "use_rnn": true, |
| "rnn_size": 512, |
| "rnn_type": "gru", |
| "rnn_num_layers": 1, |
| "decoder_mlp_layers": [], |
| "nonlinearity": "elu", |
| "policy_initialization": "orthogonal", |
| "policy_init_gain": 1.0, |
| "actor_critic_share_weights": true, |
| "adaptive_stddev": true, |
| "continuous_tanh_scale": 0.0, |
| "initial_stddev": 1.0, |
| "use_env_info_cache": false, |
| "env_gpu_actions": false, |
| "env_gpu_observations": true, |
| "env_frameskip": 1, |
| "env_framestack": 1, |
| "pixel_format": "CHW", |
| "use_record_episode_statistics": false, |
| "episode_counter": false, |
| "with_wandb": true, |
| "wandb_user": "platypus", |
| "wandb_project": "sample_factory", |
| "wandb_group": null, |
| "wandb_job_type": "SF", |
| "wandb_tags": [], |
| "with_pbt": false, |
| "pbt_mix_policies_in_one_env": true, |
| "pbt_period_env_steps": 5000000, |
| "pbt_start_mutation": 20000000, |
| "pbt_replace_fraction": 0.3, |
| "pbt_mutation_rate": 0.15, |
| "pbt_replace_reward_gap": 0.1, |
| "pbt_replace_reward_gap_absolute": 1e-06, |
| "pbt_optimize_gamma": false, |
| "pbt_target_objective": "true_objective", |
| "pbt_perturb_min": 1.1, |
| "pbt_perturb_max": 1.5, |
| "env_cfg": "{\"wall_density\": 0.01, \"altar:cost\": 100, \"cost:shield\": 0, \"num_agents\": 20, \"width\": 40, \"height\": 40, \"num_altars\": 5, \"num_chargers\": 10, \"num_generators\": 50}", |
| "command_line": "--aux_loss_coef=0 --recurrence=256 --rollout=256 --value_loss_coeff=0.976 --exploration_loss=symmetric_kl --exploration_loss_coeff=0.002 --policy_initialization=orthogonal --learning_rate=0.0001 --max_policy_lag=50 --nonlinearity=elu --load_checkpoint_kind=latest --normalize_input=False --batch_size=16384 --decorrelate_experience_max_seconds=150 --train_for_env_steps=9999999999999 --with_wandb=True --wandb_user=platypus --wandb_project=sample_factory --experiment=p2.fa.clean --rnn_num_layers=1 --rnn_size=512 --rnn_type=gru --env=GDY-PowerGrid --env_cfg={\"wall_density\": 0.01, \"altar:cost\": 100, \"cost:shield\": 0, \"num_agents\": 20, \"width\": 40, \"height\": 40, \"num_altars\": 5, \"num_chargers\": 10, \"num_generators\": 50}", |
| "cli_args": { |
| "env": "GDY-PowerGrid", |
| "experiment": "p2.fa.clean", |
| "max_policy_lag": 50, |
| "batch_size": 16384, |
| "rollout": 256, |
| "recurrence": 256, |
| "exploration_loss_coeff": 0.002, |
| "value_loss_coeff": 0.976, |
| "aux_loss_coeff": 0.0, |
| "exploration_loss": "symmetric_kl", |
| "learning_rate": 0.0001, |
| "normalize_input": false, |
| "decorrelate_experience_max_seconds": 150, |
| "train_for_env_steps": 9999999999999, |
| "load_checkpoint_kind": "latest", |
| "rnn_size": 512, |
| "rnn_type": "gru", |
| "rnn_num_layers": 1, |
| "nonlinearity": "elu", |
| "policy_initialization": "orthogonal", |
| "with_wandb": true, |
| "wandb_user": "platypus", |
| "wandb_project": "sample_factory", |
| "env_cfg": "{\"wall_density\": 0.01, \"altar:cost\": 100, \"cost:shield\": 0, \"num_agents\": 20, \"width\": 40, \"height\": 40, \"num_altars\": 5, \"num_chargers\": 10, \"num_generators\": 50}" |
| }, |
| "git_hash": "c1f8312bb9edc5b2b815fa011904740d7104e699", |
| "git_repo_name": "https://github.com/daveey/metta.git", |
| "wandb_unique_id": "p2.fa.clean_20240425_215042_340478" |
| } |
