andrewzhang505's picture
Upload cfg.json with huggingface_hub
cfc5d03
{
"help": false,
"algo": "APPO",
"env": "quadrotor_multi",
"experiment": "01_baseline_multi_drone_obstacle_see_1111",
"train_dir": "./train_dir/quad_multi_baseline_obstacle/baseline_multi_drone_obstacle_",
"restart_behavior": "resume",
"device": "gpu",
"seed": 1111,
"num_policies": 1,
"async_rl": true,
"serial_mode": false,
"batched_sampling": true,
"num_batches_to_accumulate": 8,
"worker_num_splits": 2,
"policy_workers_per_policy": 1,
"max_policy_lag": 100000000,
"num_workers": 36,
"num_envs_per_worker": 4,
"batch_size": 1024,
"num_batches_per_epoch": 1,
"num_epochs": 1,
"rollout": 128,
"recurrence": 1,
"shuffle_minibatches": false,
"gamma": 0.99,
"reward_scale": 1.0,
"reward_clip": 1000.0,
"value_bootstrap": false,
"normalize_returns": true,
"exploration_loss_coeff": 0.0,
"value_loss_coeff": 0.5,
"kl_loss_coeff": 0.0,
"exploration_loss": "entropy",
"gae_lambda": 1.0,
"ppo_clip_ratio": 0.1,
"ppo_clip_value": 5.0,
"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": 5.0,
"learning_rate": 0.0001,
"lr_schedule": "constant",
"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,
"experiment_summaries_interval": 60,
"stats_avg": 100,
"summaries_use_frameskip": true,
"heartbeat_interval": 10,
"heartbeat_reporting_interval": 60,
"train_for_env_steps": 10000000000,
"train_for_seconds": 10000000000,
"save_every_sec": 120,
"keep_checkpoints": 3,
"load_checkpoint_kind": "latest",
"save_milestones_sec": 10000,
"save_best_every_sec": 5,
"save_best_metric": "reward",
"save_best_after": 100000,
"benchmark": false,
"encoder_type": "mlp",
"encoder_subtype": "mlp_quads",
"encoder_custom": "quad_multi_encoder",
"encoder_extra_fc_layers": 0,
"hidden_size": 256,
"nonlinearity": "tanh",
"policy_initialization": "xavier_uniform",
"policy_init_gain": 1.0,
"actor_critic_share_weights": false,
"adaptive_stddev": false,
"initial_stddev": 1.0,
"use_rnn": false,
"rnn_type": "gru",
"rnn_num_layers": 1,
"use_env_info_cache": false,
"env_gpu_actions": false,
"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": null,
"wandb_job_type": "SF",
"wandb_tags": [
"multi",
"obstacles"
],
"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,
"quads_discretize_actions": -1,
"quads_clip_input": false,
"quads_effort_reward": null,
"quads_episode_duration": 15.0,
"quads_num_agents": 8,
"quads_neighbor_hidden_size": 256,
"quads_neighbor_encoder_type": "attention",
"quads_collision_reward": 5.0,
"quads_collision_obstacle_reward": 5.0,
"quads_settle_reward": 0.0,
"quads_settle": false,
"quads_vel_reward_out_range": 0.8,
"quads_settle_range_meters": 1.0,
"quads_collision_hitbox_radius": 2.0,
"quads_collision_falloff_radius": 4.0,
"quads_collision_smooth_max_penalty": 10.0,
"neighbor_obs_type": "pos_vel",
"quads_use_numba": true,
"quads_obstacle_mode": "dynamic",
"quads_obstacle_num": 1,
"quads_obstacle_type": "sphere",
"quads_obstacle_size": 0.0,
"quads_obstacle_traj": "mix",
"quads_local_obs": 6,
"quads_local_coeff": 1.0,
"quads_local_metric": "dist",
"quads_view_mode": "local",
"quads_adaptive_env": false,
"quads_mode": "mix",
"quads_formation": "circle_horizontal",
"quads_formation_size": 0.0,
"room_dims": [
10,
10,
10
],
"quads_obs_repr": "xyz_vxyz_R_omega",
"replay_buffer_sample_prob": 0.0,
"anneal_collision_steps": 300000000.0,
"quads_obstacle_obs_mode": "absolute",
"quads_obstacle_hidden_size": 256,
"quads_collision_obst_smooth_max_penalty": 10.0,
"quads_obst_penalty_fall_off": 10.0,
"use_spectral_norm": false,
"command_line": "--env=quadrotor_multi --train_for_env_steps=1000000000 --algo=APPO --use_rnn=False --num_workers=36 --num_envs_per_worker=4 --learning_rate=0.0001 --ppo_clip_value=5.0 --recurrence=1 --nonlinearity=tanh --actor_critic_share_weights=False --policy_initialization=xavier_uniform --adaptive_stddev=False --with_vtrace=False --max_policy_lag=100000000 --hidden_size=256 --gae_lambda=1.00 --max_grad_norm=5.0 --exploration_loss_coeff=0.0 --rollout=128 --batch_size=1024 --quads_use_numba=True --quads_mode=mix --quads_episode_duration=15.0 --quads_formation_size=0.0 --encoder_custom=quad_multi_encoder --quads_collision_reward=5.0 --quads_neighbor_hidden_size=256 --neighbor_obs_type=pos_vel --quads_settle_reward=0.0 --quads_collision_hitbox_radius=2.0 --quads_collision_falloff_radius=4.0 --quads_local_obs=6 --quads_local_metric=dist --quads_local_coeff=1.0 --quads_num_agents=8 --quads_collision_reward=5.0 --quads_collision_smooth_max_penalty=10.0 --quads_neighbor_encoder_type=attention --replay_buffer_sample_prob=0.75 --anneal_collision_steps=300000000 --train_for_env_steps=10000000000 --num_workers=36 --num_envs_per_worker=4 --quads_num_agents=8 --save_milestones_sec=10000 --async_rl=True --num_batches_to_accumulate=8 --serial_mode=False --batched_sampling=True --normalize_input=True --normalize_returns=True --with_wandb=True --wandb_tags multi obstacles --quads_obstacle_mode=dynamic --quads_obstacle_num=1 --quads_obstacle_type=sphere --quads_obstacle_traj=mix --quads_collision_obstacle_reward=5.0 --quads_obstacle_obs_mode=absolute --quads_collision_obst_smooth_max_penalty=10.0 --quads_obstacle_hidden_size=256 --replay_buffer_sample_prob=0.0 --quads_obst_penalty_fall_off=10.0 --seed=1111 --experiment=01_baseline_multi_drone_obstacle_see_1111 --train_dir=./train_dir/quad_multi_baseline_obstacle/baseline_multi_drone_obstacle_",
"cli_args": {
"algo": "APPO",
"env": "quadrotor_multi",
"experiment": "01_baseline_multi_drone_obstacle_see_1111",
"train_dir": "./train_dir/quad_multi_baseline_obstacle/baseline_multi_drone_obstacle_",
"seed": 1111,
"async_rl": true,
"serial_mode": false,
"batched_sampling": true,
"num_batches_to_accumulate": 8,
"max_policy_lag": 100000000,
"num_workers": 36,
"num_envs_per_worker": 4,
"batch_size": 1024,
"rollout": 128,
"recurrence": 1,
"normalize_returns": true,
"exploration_loss_coeff": 0.0,
"gae_lambda": 1.0,
"ppo_clip_value": 5.0,
"with_vtrace": false,
"max_grad_norm": 5.0,
"learning_rate": 0.0001,
"normalize_input": true,
"train_for_env_steps": 10000000000,
"save_milestones_sec": 10000,
"encoder_custom": "quad_multi_encoder",
"hidden_size": 256,
"nonlinearity": "tanh",
"policy_initialization": "xavier_uniform",
"actor_critic_share_weights": false,
"adaptive_stddev": false,
"use_rnn": false,
"with_wandb": true,
"wandb_tags": [
"multi",
"obstacles"
],
"quads_episode_duration": 15.0,
"quads_num_agents": 8,
"quads_neighbor_hidden_size": 256,
"quads_neighbor_encoder_type": "attention",
"quads_collision_reward": 5.0,
"quads_collision_obstacle_reward": 5.0,
"quads_settle_reward": 0.0,
"quads_collision_hitbox_radius": 2.0,
"quads_collision_falloff_radius": 4.0,
"quads_collision_smooth_max_penalty": 10.0,
"neighbor_obs_type": "pos_vel",
"quads_use_numba": true,
"quads_obstacle_mode": "dynamic",
"quads_obstacle_num": 1,
"quads_obstacle_type": "sphere",
"quads_obstacle_traj": "mix",
"quads_local_obs": 6,
"quads_local_coeff": 1.0,
"quads_local_metric": "dist",
"quads_mode": "mix",
"quads_formation_size": 0.0,
"replay_buffer_sample_prob": 0.0,
"anneal_collision_steps": 300000000.0,
"quads_obstacle_obs_mode": "absolute",
"quads_obstacle_hidden_size": 256,
"quads_collision_obst_smooth_max_penalty": 10.0,
"quads_obst_penalty_fall_off": 10.0
},
"git_hash": "1da4ae5b50d4d0dbca38398d7280ca2a5e6930e2",
"git_repo_name": "https://github.com/andrewzhang505/sample-factory.git",
"wandb_unique_id": "01_baseline_multi_drone_obstacle_see_1111_20220817_164609_222944"
}