| { | |
| "help": false, | |
| "algo": "APPO", | |
| "env": "doom_duel", | |
| "experiment": "doom-duel-pbt-4", | |
| "train_dir": "/home/andrewzhang/sample-factory/train_dir", | |
| "restart_behavior": "resume", | |
| "device": "gpu", | |
| "seed": null, | |
| "num_policies": 8, | |
| "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": 1000, | |
| "num_workers": 72, | |
| "num_envs_per_worker": 16, | |
| "batch_size": 2048, | |
| "num_batches_per_epoch": 1, | |
| "num_epochs": 1, | |
| "rollout": 32, | |
| "recurrence": 32, | |
| "shuffle_minibatches": false, | |
| "gamma": 0.995, | |
| "reward_scale": 0.5, | |
| "reward_clip": 1000.0, | |
| "value_bootstrap": false, | |
| "normalize_returns": true, | |
| "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": 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, | |
| "obs_subtract_mean": 0.0, | |
| "obs_scale": 255.0, | |
| "normalize_input": true, | |
| "normalize_input_keys": null, | |
| "decorrelate_experience_max_seconds": 0, | |
| "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": 10, | |
| "heartbeat_reporting_interval": 600, | |
| "train_for_env_steps": 10000000000, | |
| "train_for_seconds": 360000, | |
| "save_every_sec": 120, | |
| "keep_checkpoints": 2, | |
| "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_frameskip": 2, | |
| "env_framestack": 1, | |
| "pixel_format": "CHW", | |
| "use_record_episode_statistics": false, | |
| "with_wandb": true, | |
| "wandb_user": null, | |
| "wandb_project": "sample_factory", | |
| "wandb_group": null, | |
| "wandb_job_type": "SF", | |
| "wandb_tags": [], | |
| "with_pbt": true, | |
| "pbt_mix_policies_in_one_env": true, | |
| "pbt_period_env_steps": 5000000, | |
| "pbt_start_mutation": 100000000, | |
| "pbt_replace_fraction": 0.3, | |
| "pbt_mutation_rate": 0.15, | |
| "pbt_replace_reward_gap": 0.5, | |
| "pbt_replace_reward_gap_absolute": 0.35, | |
| "pbt_optimize_gamma": false, | |
| "pbt_target_objective": "true_objective", | |
| "pbt_perturb_min": 1.1, | |
| "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, | |
| "eval_env_frameskip": 1, | |
| "fps": 35, | |
| "command_line": "--env=doom_duel --train_for_seconds=360000 --algo=APPO --gamma=0.995 --env_frameskip=2 --use_rnn=True --reward_scale=0.5 --num_workers=72 --num_envs_per_worker=16 --num_policies=8 --batch_size=2048 --res_w=128 --res_h=72 --wide_aspect_ratio=False --benchmark=False --pbt_replace_reward_gap=0.5 --pbt_replace_reward_gap_absolute=0.35 --pbt_period_env_steps=5000000 --with_pbt=True --pbt_start_mutation=100000000 --with_wandb=True --experiment=doom-duel-pbt-4 --heartbeat_reporting_interval=600", | |
| "cli_args": { | |
| "algo": "APPO", | |
| "env": "doom_duel", | |
| "experiment": "doom-duel-pbt-4", | |
| "num_policies": 8, | |
| "num_workers": 72, | |
| "num_envs_per_worker": 16, | |
| "batch_size": 2048, | |
| "gamma": 0.995, | |
| "reward_scale": 0.5, | |
| "heartbeat_reporting_interval": 600, | |
| "train_for_seconds": 360000, | |
| "benchmark": false, | |
| "use_rnn": true, | |
| "env_frameskip": 2, | |
| "with_wandb": true, | |
| "with_pbt": true, | |
| "pbt_period_env_steps": 5000000, | |
| "pbt_start_mutation": 100000000, | |
| "pbt_replace_reward_gap": 0.5, | |
| "pbt_replace_reward_gap_absolute": 0.35, | |
| "res_w": 128, | |
| "res_h": 72, | |
| "wide_aspect_ratio": false | |
| }, | |
| "git_hash": "c2661559dbf483eb038a0b34bd8cdd60a6551d3f", | |
| "git_repo_name": "https://github.com/andrewzhang505/sample-factory.git", | |
| "wandb_unique_id": "doom-duel-pbt-4_20221025_141253_205171" | |
| } |