Upload cfg.json with huggingface_hub

cfg.json

@@ -0,0 +1,156 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "AllegroHand",
+  "experiment": "04_allegrohand_v079_norm_returns_see_3333_s.mod_True_a.rl_False_n.ret_True",
+  "train_dir": "./train_dir/allegrohand_v079_norm_returns/allegrohand_v079_norm_returns_slurm",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": 3333,
+  "num_policies": 1,
+  "async_rl": false,
+  "serial_mode": true,
+  "batched_sampling": true,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 1,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 1,
+  "num_envs_per_worker": 1,
+  "batch_size": 32768,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 5,
+  "rollout": 16,
+  "recurrence": 16,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 0.01,
+  "reward_clip": 1000.0,
+  "value_bootstrap": true,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.0,
+  "value_loss_coeff": 2.0,
+  "kl_loss_coeff": 0.0,
+  "exploration_loss": "entropy",
+  "gae_lambda": 0.95,
+  "ppo_clip_ratio": 0.2,
+  "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": 1.0,
+  "learning_rate": 0.005,
+  "lr_schedule": "kl_adaptive_epoch",
+  "lr_schedule_kl_threshold": 0.02,
+  "obs_subtract_mean": 0.0,
+  "obs_scale": 1.0,
+  "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": 150000000,
+  "train_for_seconds": 10000000000,
+  "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": 5000000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    512,
+    256,
+    128
+  ],
+  "encoder_conv_architecture": "convnet_simple",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": false,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "elu",
+  "policy_initialization": "torch_default",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": false,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": true,
+  "env_gpu_actions": true,
+  "env_gpu_observations": true,
+  "env_frameskip": 1,
+  "env_framestack": 1,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": false,
+  "with_wandb": true,
+  "wandb_user": null,
+  "wandb_project": "sample_factory",
+  "wandb_group": "isaacgym_allegrohand_sf2_v079_norm_returns",
+  "wandb_job_type": "SF",
+  "wandb_tags": [
+    "allegrohand",
+    "v079_norm_returns"
+  ],
+  "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_agents": -1,
+  "obs_key": "obs",
+  "subtask": null,
+  "ige_api_version": "preview4",
+  "eval_stats": false,
+  "command_line": "--actor_worker_gpus 0 --wandb_project=sample_factory --env=AllegroHand --train_for_env_steps=150000000 --with_wandb=True --wandb_group=isaacgym_allegrohand_sf2_v079_norm_returns --wandb_tags allegrohand v079_norm_returns --seed=3333 --serial_mode=True --async_rl=False --normalize_returns=True --experiment=04_allegrohand_v079_norm_returns_see_3333_s.mod_True_a.rl_False_n.ret_True --train_dir=./train_dir/allegrohand_v079_norm_returns/allegrohand_v079_norm_returns_slurm",
+  "cli_args": {
+    "env": "AllegroHand",
+    "experiment": "04_allegrohand_v079_norm_returns_see_3333_s.mod_True_a.rl_False_n.ret_True",
+    "train_dir": "./train_dir/allegrohand_v079_norm_returns/allegrohand_v079_norm_returns_slurm",
+    "seed": 3333,
+    "async_rl": false,
+    "serial_mode": true,
+    "normalize_returns": true,
+    "actor_worker_gpus": [
+      0
+    ],
+    "train_for_env_steps": 150000000,
+    "with_wandb": true,
+    "wandb_project": "sample_factory",
+    "wandb_group": "isaacgym_allegrohand_sf2_v079_norm_returns",
+    "wandb_tags": [
+      "allegrohand",
+      "v079_norm_returns"
+    ]
+  },
+  "git_hash": "0b1d3fc4f93b814b0987f4f5ac91119ac2078725",
+  "git_repo_name": "https://github.com/andrewzhang505/sample-factory.git",
+  "wandb_unique_id": "04_allegrohand_v079_norm_returns_see_3333_s.mod_True_a.rl_False_n.ret_True_20221128_165025_758186"
+}