|
{ |
|
"help": false, |
|
"algo": "APPO", |
|
"env": "atari_pitfall", |
|
"experiment": "20221014_2B__atari_pitfall_2222", |
|
"train_dir": "/gpfsscratch/rech/ajs/utv52ia/sample_factory/train_dir/atari_2b", |
|
"restart_behavior": "resume", |
|
"device": "gpu", |
|
"seed": 2222, |
|
"num_policies": 1, |
|
"async_rl": true, |
|
"serial_mode": false, |
|
"batched_sampling": true, |
|
"num_batches_to_accumulate": 2, |
|
"worker_num_splits": 1, |
|
"policy_workers_per_policy": 1, |
|
"max_policy_lag": 1000, |
|
"num_workers": 4, |
|
"num_envs_per_worker": 1, |
|
"batch_size": 1024, |
|
"num_batches_per_epoch": 8, |
|
"num_epochs": 2, |
|
"rollout": 64, |
|
"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": 0.0004677351413, |
|
"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": 0.0, |
|
"learning_rate": 0.0003033891184, |
|
"lr_schedule": "linear_decay", |
|
"lr_schedule_kl_threshold": 0.008, |
|
"obs_subtract_mean": 0.0, |
|
"obs_scale": 255.0, |
|
"normalize_input": true, |
|
"normalize_input_keys": [ |
|
"obs" |
|
], |
|
"decorrelate_experience_max_seconds": 1, |
|
"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": 10, |
|
"heartbeat_reporting_interval": 60, |
|
"train_for_env_steps": 2000000000, |
|
"train_for_seconds": 3600000, |
|
"save_every_sec": 120, |
|
"keep_checkpoints": 2, |
|
"load_checkpoint_kind": "latest", |
|
"save_milestones_sec": 1200, |
|
"save_best_every_sec": 5, |
|
"save_best_metric": "reward", |
|
"save_best_after": 100000, |
|
"benchmark": false, |
|
"encoder_mlp_layers": [ |
|
512, |
|
512 |
|
], |
|
"encoder_conv_architecture": "convnet_atari", |
|
"encoder_conv_mlp_layers": [ |
|
512 |
|
], |
|
"use_rnn": false, |
|
"rnn_size": 512, |
|
"rnn_type": "gru", |
|
"rnn_num_layers": 1, |
|
"decoder_mlp_layers": [], |
|
"nonlinearity": "relu", |
|
"policy_initialization": "orthogonal", |
|
"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_frameskip": 4, |
|
"env_framestack": 4, |
|
"pixel_format": "CHW", |
|
"use_record_episode_statistics": true, |
|
"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_batch_size": false, |
|
"pbt_optimize_gamma": false, |
|
"pbt_target_objective": "true_objective", |
|
"pbt_perturb_min": 1.05, |
|
"pbt_perturb_max": 1.5, |
|
"env_agents": 512, |
|
"command_line": "--seed=2222 --experiment=20221014_2B__atari_pitfall_2222 --env=atari_pitfall --train_for_seconds=3600000 --algo=APPO --gamma=0.99 --num_workers=4 --num_envs_per_worker=1 --worker_num_splits=1 --env_agents=512 --benchmark=False --max_grad_norm=0.0 --decorrelate_experience_max_seconds=1 --encoder_conv_architecture=convnet_atari --encoder_conv_mlp_layers 512 --nonlinearity=relu --num_policies=1 --normalize_input=True --normalize_input_keys obs --normalize_returns=True --async_rl=True --batched_sampling=True --train_for_env_steps=2000000000 --save_milestones_sec=1200 --train_dir /gpfsscratch/rech/ajs/utv52ia/sample_factory/train_dir/atari_2b --rollout 64 --exploration_loss_coeff 0.0004677351413 --num_epochs 2 --batch_size 1024 --num_batches_per_epoch 8 --learning_rate 0.0003033891184", |
|
"cli_args": { |
|
"algo": "APPO", |
|
"env": "atari_pitfall", |
|
"experiment": "20221014_2B__atari_pitfall_2222", |
|
"train_dir": "/gpfsscratch/rech/ajs/utv52ia/sample_factory/train_dir/atari_2b", |
|
"seed": 2222, |
|
"num_policies": 1, |
|
"async_rl": true, |
|
"batched_sampling": true, |
|
"worker_num_splits": 1, |
|
"num_workers": 4, |
|
"num_envs_per_worker": 1, |
|
"batch_size": 1024, |
|
"num_batches_per_epoch": 8, |
|
"num_epochs": 2, |
|
"rollout": 64, |
|
"gamma": 0.99, |
|
"normalize_returns": true, |
|
"exploration_loss_coeff": 0.0004677351413, |
|
"max_grad_norm": 0.0, |
|
"learning_rate": 0.0003033891184, |
|
"normalize_input": true, |
|
"normalize_input_keys": [ |
|
"obs" |
|
], |
|
"decorrelate_experience_max_seconds": 1, |
|
"train_for_env_steps": 2000000000, |
|
"train_for_seconds": 3600000, |
|
"save_milestones_sec": 1200, |
|
"benchmark": false, |
|
"encoder_conv_architecture": "convnet_atari", |
|
"encoder_conv_mlp_layers": [ |
|
512 |
|
], |
|
"nonlinearity": "relu", |
|
"env_agents": 512 |
|
}, |
|
"git_hash": "unknown", |
|
"git_repo_name": "not a git repository" |
|
} |