{
  "help": false,
  "algo": "APPO",
  "env": "walker2d",
  "experiment": "06_v083_brax_basic_benchmark_see_2322090_env_walker2d_u.rnn_False_n.epo_5",
  "train_dir": "./train_dir/v083_brax_basic_benchmark/v083_brax_basic_benchmark_slurm",
  "restart_behavior": "resume",
  "device": "gpu",
  "seed": 2322090,
  "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": 2,
  "num_epochs": 5,
  "rollout": 32,
  "recurrence": 1,
  "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": 0.0003,
  "lr_schedule": "kl_adaptive_epoch",
  "lr_schedule_kl_threshold": 0.008,
  "lr_adaptive_min": 1e-06,
  "lr_adaptive_max": 0.002,
  "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": 20,
  "heartbeat_reporting_interval": 180,
  "train_for_env_steps": 100000000,
  "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": [
    256,
    128,
    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": "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": false,
  "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": 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,
  "env_agents": 2048,
  "clamp_actions": false,
  "clamp_rew_obs": false,
  "command_line": "--actor_worker_gpus 0 --wandb_project=sample_factory --with_wandb=True --seed=2322090 --env=walker2d --use_rnn=False --num_epochs=5 --experiment=06_v083_brax_basic_benchmark_see_2322090_env_walker2d_u.rnn_False_n.epo_5 --train_dir=./train_dir/v083_brax_basic_benchmark/v083_brax_basic_benchmark_slurm",
  "cli_args": {
    "env": "walker2d",
    "experiment": "06_v083_brax_basic_benchmark_see_2322090_env_walker2d_u.rnn_False_n.epo_5",
    "train_dir": "./train_dir/v083_brax_basic_benchmark/v083_brax_basic_benchmark_slurm",
    "seed": 2322090,
    "num_epochs": 5,
    "actor_worker_gpus": [
      0
    ],
    "use_rnn": false,
    "with_wandb": true,
    "wandb_project": "sample_factory"
  },
  "git_hash": "6aa87f2d416b9fad874b299d864a522c887c238a",
  "git_repo_name": "git@github.com:alex-petrenko/sample-factory.git",
  "train_script": "sf_examples.brax.train_brax",
  "wandb_unique_id": "06_v083_brax_basic_benchmark_see_2322090_env_walker2d_u.rnn_False_n.epo_5_20230111_192722_009099"
}