wmFrank's picture
Upload cfg.json with huggingface_hub
23411bc
{
"help": false,
"algo": "APPO",
"env": "TowerBuilding",
"experiment": "TowerBuilding_real_sf2",
"train_dir": "/home/mingwang/real-sf2/megaverse/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": 2,
"max_policy_lag": 1000,
"num_workers": 12,
"num_envs_per_worker": 2,
"batch_size": 4096,
"num_batches_per_epoch": 1,
"num_epochs": 1,
"rollout": 32,
"recurrence": 32,
"shuffle_minibatches": false,
"gamma": 0.997,
"reward_scale": 1.0,
"reward_clip": 30.0,
"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": 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": 0.0,
"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": [
0
],
"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": 60,
"train_for_env_steps": 2000000000,
"train_for_seconds": 360000000,
"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": 2,
"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": false,
"env_frameskip": 1,
"env_framestack": 1,
"pixel_format": "CHW",
"use_record_episode_statistics": false,
"with_wandb": true,
"wandb_user": null,
"wandb_project": "megaverse-benchmark",
"wandb_group": "megaverse",
"wandb_job_type": "SF",
"wandb_tags": [
"real_sf2_test1"
],
"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,
"megaverse_num_envs_per_instance": 32,
"megaverse_num_agents_per_env": 1,
"megaverse_num_simulation_threads": 1,
"megaverse_use_vulkan": true,
"megaverse_increase_team_spirit": false,
"megaverse_max_team_spirit_steps": 1000000000.0,
"encoder_type": "conv",
"encoder_subtype": "convnet_simple",
"hidden_size": 512,
"command_line": "--train_for_seconds=360000000 --train_for_env_steps=2000000000 --algo=APPO --gamma=0.997 --use_rnn=True --rnn_num_layers=2 --num_workers=12 --num_envs_per_worker=2 --num_epochs=1 --rollout=32 --recurrence=32 --batch_size=4096 --actor_worker_gpus 0 --env_gpu_observations=False --num_policies=1 --with_pbt=False --max_grad_norm=0.0 --exploration_loss=symmetric_kl --exploration_loss_coeff=0.001 --megaverse_num_simulation_threads=1 --megaverse_num_envs_per_instance=32 --megaverse_num_agents_per_env=1 --megaverse_use_vulkan=True --policy_workers_per_policy=2 --reward_clip=30 --env=TowerBuilding --experiment=TowerBuilding_real_sf2 --with_wandb=True --wandb_project=megaverse-benchmark --wandb_group=megaverse --wandb_tags real_sf2_test0",
"cli_args": {
"algo": "APPO",
"env": "TowerBuilding",
"experiment": "TowerBuilding_real_sf2",
"num_policies": 1,
"policy_workers_per_policy": 2,
"num_workers": 12,
"num_envs_per_worker": 2,
"batch_size": 4096,
"num_epochs": 1,
"rollout": 32,
"recurrence": 32,
"gamma": 0.997,
"reward_clip": 30.0,
"exploration_loss_coeff": 0.001,
"exploration_loss": "symmetric_kl",
"max_grad_norm": 0.0,
"actor_worker_gpus": [
0
],
"train_for_env_steps": 2000000000,
"train_for_seconds": 360000000,
"use_rnn": true,
"rnn_num_layers": 2,
"env_gpu_observations": false,
"with_wandb": true,
"wandb_project": "megaverse-benchmark",
"wandb_group": "megaverse",
"wandb_tags": [
"real_sf2_test0"
],
"with_pbt": false,
"megaverse_num_envs_per_instance": 32,
"megaverse_num_agents_per_env": 1,
"megaverse_num_simulation_threads": 1,
"megaverse_use_vulkan": true
},
"git_hash": "1eb0dc14ba99f2279e8ba98e8a706961dc49483a",
"git_repo_name": "https://github.com/wmFrank/megaverse.git",
"wandb_unique_id": "TowerBuilding_real_sf2_20221027_144938_178247"
}