edbeeching/atari_2B_atari_solaris_1111
07
1{2 "help": false,3 "algo": "APPO",4 "env": "atari_solaris",5 "experiment": "20221014_2B__atari_solaris_1111",6 "train_dir": "/gpfsscratch/rech/ajs/utv52ia/sample_factory/train_dir/atari_2b",7 "restart_behavior": "resume",8 "device": "gpu",9 "seed": 1111,10 "num_policies": 1,11 "async_rl": true,12 "serial_mode": false,13 "batched_sampling": true,14 "num_batches_to_accumulate": 2,15 "worker_num_splits": 1,16 "policy_workers_per_policy": 1,17 "max_policy_lag": 1000,18 "num_workers": 4,19 "num_envs_per_worker": 1,20 "batch_size": 1024,21 "num_batches_per_epoch": 8,22 "num_epochs": 2,23 "rollout": 64,24 "recurrence": 1,25 "shuffle_minibatches": false,26 "gamma": 0.99,27 "reward_scale": 1.0,28 "reward_clip": 1000.0,29 "value_bootstrap": false,30 "normalize_returns": true,31 "exploration_loss_coeff": 0.0004677351413,32 "value_loss_coeff": 0.5,33 "kl_loss_coeff": 0.0,34 "exploration_loss": "entropy",35 "gae_lambda": 0.95,36 "ppo_clip_ratio": 0.1,37 "ppo_clip_value": 1.0,38 "with_vtrace": false,39 "vtrace_rho": 1.0,40 "vtrace_c": 1.0,41 "optimizer": "adam",42 "adam_eps": 1e-05,43 "adam_beta1": 0.9,44 "adam_beta2": 0.999,45 "max_grad_norm": 0.0,46 "learning_rate": 0.0003033891184,47 "lr_schedule": "linear_decay",48 "lr_schedule_kl_threshold": 0.008,49 "obs_subtract_mean": 0.0,50 "obs_scale": 255.0,51 "normalize_input": true,52 "normalize_input_keys": [53 "obs"54 ],55 "decorrelate_experience_max_seconds": 1,56 "decorrelate_envs_on_one_worker": true,57 "actor_worker_gpus": [],58 "set_workers_cpu_affinity": true,59 "force_envs_single_thread": false,60 "default_niceness": 0,61 "log_to_file": true,62 "experiment_summaries_interval": 3,63 "flush_summaries_interval": 30,64 "stats_avg": 100,65 "summaries_use_frameskip": true,66 "heartbeat_interval": 10,67 "heartbeat_reporting_interval": 60,68 "train_for_env_steps": 2000000000,69 "train_for_seconds": 3600000,70 "save_every_sec": 120,71 "keep_checkpoints": 2,72 "load_checkpoint_kind": "latest",73 "save_milestones_sec": 1200,74 "save_best_every_sec": 5,75 "save_best_metric": "reward",76 "save_best_after": 100000,77 "benchmark": false,78 "encoder_mlp_layers": [79 512,80 51281 ],82 "encoder_conv_architecture": "convnet_atari",83 "encoder_conv_mlp_layers": [84 51285 ],86 "use_rnn": false,87 "rnn_size": 512,88 "rnn_type": "gru",89 "rnn_num_layers": 1,90 "decoder_mlp_layers": [],91 "nonlinearity": "relu",92 "policy_initialization": "orthogonal",93 "policy_init_gain": 1.0,94 "actor_critic_share_weights": true,95 "adaptive_stddev": false,96 "continuous_tanh_scale": 0.0,97 "initial_stddev": 1.0,98 "use_env_info_cache": false,99 "env_gpu_actions": false,100 "env_frameskip": 4,101 "env_framestack": 4,102 "pixel_format": "CHW",103 "use_record_episode_statistics": true,104 "with_wandb": false,105 "wandb_user": null,106 "wandb_project": "sample_factory",107 "wandb_group": null,108 "wandb_job_type": "SF",109 "wandb_tags": [],110 "with_pbt": false,111 "pbt_mix_policies_in_one_env": true,112 "pbt_period_env_steps": 5000000,113 "pbt_start_mutation": 20000000,114 "pbt_replace_fraction": 0.3,115 "pbt_mutation_rate": 0.15,116 "pbt_replace_reward_gap": 0.1,117 "pbt_replace_reward_gap_absolute": 1e-06,118 "pbt_optimize_batch_size": false,119 "pbt_optimize_gamma": false,120 "pbt_target_objective": "true_objective",121 "pbt_perturb_min": 1.05,122 "pbt_perturb_max": 1.5,123 "env_agents": 512,124 "command_line": "--seed=1111 --experiment=20221014_2B__atari_solaris_1111 --env=atari_solaris --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",125 "cli_args": {126 "algo": "APPO",127 "env": "atari_solaris",128 "experiment": "20221014_2B__atari_solaris_1111",129 "train_dir": "/gpfsscratch/rech/ajs/utv52ia/sample_factory/train_dir/atari_2b",130 "seed": 1111,131 "num_policies": 1,132 "async_rl": true,133 "batched_sampling": true,134 "worker_num_splits": 1,135 "num_workers": 4,136 "num_envs_per_worker": 1,137 "batch_size": 1024,138 "num_batches_per_epoch": 8,139 "num_epochs": 2,140 "rollout": 64,141 "gamma": 0.99,142 "normalize_returns": true,143 "exploration_loss_coeff": 0.0004677351413,144 "max_grad_norm": 0.0,145 "learning_rate": 0.0003033891184,146 "normalize_input": true,147 "normalize_input_keys": [148 "obs"149 ],150 "decorrelate_experience_max_seconds": 1,151 "train_for_env_steps": 2000000000,152 "train_for_seconds": 3600000,153 "save_milestones_sec": 1200,154 "benchmark": false,155 "encoder_conv_architecture": "convnet_atari",156 "encoder_conv_mlp_layers": [157 512158 ],159 "nonlinearity": "relu",160 "env_agents": 512161 },162 "git_hash": "unknown",163 "git_repo_name": "not a git repository"164}