| { | |
| "help": false, | |
| "algo": "APPO", | |
| "env": "doom_deadly_corridor", | |
| "experiment": "01_doom_basic_envs_see_0_env_doom_deadly_corridor", | |
| "train_dir": "./train_dir/doom_basic_envs/doom_basic_envs_drone_basic", | |
| "restart_behavior": "resume", | |
| "device": "gpu", | |
| "seed": 0, | |
| "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": 10000, | |
| "num_workers": 16, | |
| "num_envs_per_worker": 16, | |
| "batch_size": 2048, | |
| "num_batches_per_epoch": 1, | |
| "num_epochs": 1, | |
| "rollout": 32, | |
| "recurrence": 32, | |
| "shuffle_minibatches": true, | |
| "gamma": 0.99, | |
| "reward_scale": 1.0, | |
| "reward_clip": 1000.0, | |
| "value_bootstrap": false, | |
| "normalize_returns": false, | |
| "exploration_loss_coeff": 0.001, | |
| "value_loss_coeff": 0.5, | |
| "kl_loss_coeff": 0.0, | |
| "exploration_loss": "symmetric_kl", | |
| "gae_lambda": 0.95, | |
| "ppo_clip_ratio": 0.1, | |
| "ppo_clip_value": 0.2, | |
| "with_vtrace": true, | |
| "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, | |
| "obs_subtract_mean": 0.0, | |
| "obs_scale": 255.0, | |
| "normalize_input": false, | |
| "decorrelate_experience_max_seconds": 10, | |
| "decorrelate_envs_on_one_worker": true, | |
| "actor_worker_gpus": [], | |
| "set_workers_cpu_affinity": true, | |
| "force_envs_single_thread": true, | |
| "default_niceness": 0, | |
| "experiment_summaries_interval": 10, | |
| "stats_avg": 100, | |
| "train_for_env_steps": 500000000, | |
| "train_for_seconds": 10000000000, | |
| "save_every_sec": 120, | |
| "keep_checkpoints": 3, | |
| "load_checkpoint_kind": "latest", | |
| "save_milestones_sec": -1, | |
| "save_best_every_sec": 5, | |
| "save_best_metric": "reward", | |
| "save_best_after": 100000, | |
| "benchmark": false, | |
| "encoder_type": "conv", | |
| "encoder_subtype": "convnet_simple", | |
| "encoder_custom": "vizdoom", | |
| "encoder_extra_fc_layers": 1, | |
| "hidden_size": 512, | |
| "nonlinearity": "elu", | |
| "policy_initialization": "orthogonal", | |
| "policy_init_gain": 1.0, | |
| "actor_critic_share_weights": true, | |
| "adaptive_stddev": true, | |
| "initial_stddev": 1.0, | |
| "use_rnn": true, | |
| "rnn_type": "gru", | |
| "rnn_num_layers": 1, | |
| "env_gpu_actions": false, | |
| "env_frameskip": 4, | |
| "env_framestack": 4, | |
| "pixel_format": "CHW", | |
| "with_wandb": true, | |
| "wandb_user": null, | |
| "wandb_project": "sample_factory", | |
| "wandb_group": null, | |
| "wandb_job_type": "SF", | |
| "wandb_tags": [ | |
| "doom", | |
| "basic" | |
| ], | |
| "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_batch_size": false, | |
| "pbt_optimize_gamma": false, | |
| "pbt_target_objective": "true_objective", | |
| "pbt_perturb_min": 1.05, | |
| "pbt_perturb_max": 1.5, | |
| "num_agents": -1, | |
| "num_humans": 0, | |
| "num_bots": -1, | |
| "start_bot_difficulty": null, | |
| "timelimit": null, | |
| "res_w": 128, | |
| "res_h": 72, | |
| "wide_aspect_ratio": false, | |
| "fps": 35, | |
| "command_line": "--train_for_env_steps=500000000 --algo=APPO --env_frameskip=4 --use_rnn=True --num_workers=16 --num_envs_per_worker=16 --num_policies=1 --num_epochs=1 --rollout=32 --recurrence=32 --batch_size=2048 --wide_aspect_ratio=False --with_wandb=True --wandb_tags doom basic --seed=0 --env=doom_deadly_corridor --experiment=01_doom_basic_envs_see_0_env_doom_deadly_corridor --train_dir=./train_dir/doom_basic_envs/doom_basic_envs_drone_basic", | |
| "cli_args": { | |
| "algo": "APPO", | |
| "env": "doom_deadly_corridor", | |
| "experiment": "01_doom_basic_envs_see_0_env_doom_deadly_corridor", | |
| "train_dir": "./train_dir/doom_basic_envs/doom_basic_envs_drone_basic", | |
| "seed": 0, | |
| "num_policies": 1, | |
| "num_workers": 16, | |
| "num_envs_per_worker": 16, | |
| "batch_size": 2048, | |
| "num_epochs": 1, | |
| "rollout": 32, | |
| "recurrence": 32, | |
| "train_for_env_steps": 500000000, | |
| "use_rnn": true, | |
| "env_frameskip": 4, | |
| "with_wandb": true, | |
| "wandb_tags": [ | |
| "doom", | |
| "basic" | |
| ], | |
| "wide_aspect_ratio": false | |
| }, | |
| "git_hash": "unknown", | |
| "git_repo_name": "not a git repository", | |
| "wandb_unique_id": "01_doom_basic_envs_see_0_env_doom_deadly_corridor_20220722_162657_031082" | |
| } |