wmFrank's picture
Upload cfg.json with huggingface_hub
13a684b
{
"help": false,
"algo": "APPO",
"env": "atari_pong",
"experiment": "01_atari_envs_see_123_env_atari_pong",
"train_dir": "./train_dir/atari_envs/atari_envs_",
"restart_behavior": "resume",
"device": "gpu",
"seed": 123,
"num_policies": 1,
"async_rl": false,
"serial_mode": false,
"batched_sampling": false,
"num_batches_to_accumulate": 2,
"worker_num_splits": 1,
"policy_workers_per_policy": 1,
"max_policy_lag": 10000,
"num_workers": 8,
"num_envs_per_worker": 1,
"batch_size": 256,
"num_batches_per_epoch": 4,
"num_epochs": 4,
"rollout": 128,
"recurrence": 1,
"shuffle_minibatches": false,
"gamma": 0.99,
"reward_scale": 1.0,
"reward_clip": 1000.0,
"value_bootstrap": false,
"normalize_returns": false,
"exploration_loss_coeff": 0.01,
"value_loss_coeff": 0.5,
"kl_loss_coeff": 0.0,
"exploration_loss": "entropy",
"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-05,
"adam_beta1": 0.9,
"adam_beta2": 0.999,
"max_grad_norm": 0.5,
"learning_rate": 0.00025,
"lr_schedule": "linear_decay",
"lr_schedule_kl_threshold": 0.008,
"obs_subtract_mean": 0.0,
"obs_scale": 255.0,
"normalize_input": false,
"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": true,
"default_niceness": 0,
"experiment_summaries_interval": 3,
"stats_avg": 100,
"summaries_use_frameskip": false,
"train_for_env_steps": 10000000,
"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_atari",
"encoder_custom": null,
"encoder_extra_fc_layers": 1,
"hidden_size": 512,
"nonlinearity": "relu",
"policy_initialization": "orthogonal",
"policy_init_gain": 1.0,
"actor_critic_share_weights": true,
"adaptive_stddev": false,
"initial_stddev": 1.0,
"use_rnn": false,
"rnn_type": "gru",
"rnn_num_layers": 1,
"env_gpu_actions": false,
"env_frameskip": 4,
"env_framestack": 4,
"pixel_format": "CHW",
"use_record_episode_statistics": true,
"with_wandb": true,
"wandb_user": null,
"wandb_project": "atari-benchmark",
"wandb_group": "atari_all",
"wandb_job_type": "SF",
"wandb_tags": [
"run5"
],
"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,
"command_line": "--algo=APPO --with_wandb=True --wandb_project=atari-benchmark --wandb_group=atari_all --wandb_tags run5 --seed=123 --env=atari_pong --experiment=01_atari_envs_see_123_env_atari_pong --train_dir=./train_dir/atari_envs/atari_envs_",
"cli_args": {
"algo": "APPO",
"env": "atari_pong",
"experiment": "01_atari_envs_see_123_env_atari_pong",
"train_dir": "./train_dir/atari_envs/atari_envs_",
"seed": 123,
"with_wandb": true,
"wandb_project": "atari-benchmark",
"wandb_group": "atari_all",
"wandb_tags": [
"run5"
]
},
"git_hash": "unknown",
"git_repo_name": "not a git repository",
"wandb_unique_id": "01_atari_envs_see_123_env_atari_pong_20220727_174745_048413"
}