| { | |
| "help": false, | |
| "algo": "APPO", | |
| "env": "mujoco_ant", | |
| "experiment": "ant_test", | |
| "train_dir": "/home/andrew_huggingface_co/sample-factory/train_dir", | |
| "restart_behavior": "resume", | |
| "device": "gpu", | |
| "seed": null, | |
| "num_policies": 1, | |
| "async_rl": false, | |
| "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": 8, | |
| "num_envs_per_worker": 8, | |
| "batch_size": 1024, | |
| "num_batches_per_epoch": 4, | |
| "num_epochs": 2, | |
| "rollout": 64, | |
| "recurrence": 1, | |
| "shuffle_minibatches": false, | |
| "gamma": 0.99, | |
| "reward_scale": 1, | |
| "reward_clip": 1000.0, | |
| "value_bootstrap": true, | |
| "normalize_returns": true, | |
| "exploration_loss_coeff": 0.0, | |
| "value_loss_coeff": 1.3, | |
| "kl_loss_coeff": 0.1, | |
| "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": 3.5, | |
| "learning_rate": 0.00295, | |
| "lr_schedule": "linear_decay", | |
| "lr_schedule_kl_threshold": 0.008, | |
| "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": [], | |
| "set_workers_cpu_affinity": true, | |
| "force_envs_single_thread": false, | |
| "default_niceness": 0, | |
| "log_to_file": true, | |
| "experiment_summaries_interval": 3, | |
| "flush_summaries_interval": 30, | |
| "stats_avg": 100, | |
| "summaries_use_frameskip": true, | |
| "heartbeat_interval": 20, | |
| "heartbeat_reporting_interval": 180, | |
| "train_for_env_steps": 10000000, | |
| "train_for_seconds": 10000000000, | |
| "save_every_sec": 15, | |
| "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": [ | |
| 64, | |
| 64 | |
| ], | |
| "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": "tanh", | |
| "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": false, | |
| "env_gpu_actions": false, | |
| "env_gpu_observations": true, | |
| "env_frameskip": 1, | |
| "env_framestack": 1, | |
| "pixel_format": "CHW", | |
| "use_record_episode_statistics": false, | |
| "with_wandb": false, | |
| "wandb_user": null, | |
| "wandb_project": "sample_factory", | |
| "wandb_group": null, | |
| "wandb_job_type": "SF", | |
| "wandb_tags": [], | |
| "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, | |
| "command_line": "--algo=APPO --env=mujoco_ant --experiment=ant_test", | |
| "cli_args": { | |
| "algo": "APPO", | |
| "env": "mujoco_ant", | |
| "experiment": "ant_test" | |
| }, | |
| "git_hash": "7355a9d939997e11f02d311f71e4ca3be2e9258f", | |
| "git_repo_name": "https://github.com/andrewzhang505/sample-factory.git" | |
| } |