andrewzhang505's picture
Update cfg.json
6afddbb
{
"help": false,
"algo": "APPO",
"env": "mujoco_halfcheetah",
"experiment": "17_mujoco_all_envs_see_4444_env_mujoco_halfcheetah",
"train_dir": "./train_dir",
"experiments_root": "mujoco_all_envs/mujoco_all_envs_crl_4",
"device": "gpu",
"seed": 4444,
"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": 10000,
"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": false,
"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,
"decorrelate_experience_max_seconds": 10,
"decorrelate_envs_on_one_worker": true,
"actor_worker_gpus": [],
"set_workers_cpu_affinity": true,
"force_envs_single_thread": true,
"default_niceness": 0,
"experiment_summaries_interval": 3,
"stats_avg": 100,
"train_for_env_steps": 10000000,
"train_for_seconds": 10000000000,
"save_every_sec": 15,
"keep_checkpoints": 3,
"load_checkpoint_kind": "latest",
"save_milestones_sec": -1,
"save_best_every_sec": 5,
"save_best_metric": "reward",
"save_best_after": 100000,
"benchmark": false,
"encoder_type": "mlp",
"encoder_subtype": "mlp_mujoco",
"encoder_custom": null,
"encoder_extra_fc_layers": 0,
"hidden_size": 64,
"nonlinearity": "tanh",
"policy_initialization": "torch_default",
"policy_init_gain": 1.0,
"actor_critic_share_weights": true,
"adaptive_stddev": false,
"initial_stddev": 1.0,
"use_rnn": false,
"rnn_type": "gru",
"rnn_num_layers": 1,
"env_gpu_actions": false,
"env_frameskip": 1,
"env_framestack": 4,
"pixel_format": "CHW",
"with_wandb": true,
"wandb_user": null,
"wandb_project": "sample_factory",
"wandb_group": null,
"wandb_job_type": "SF",
"wandb_tags": [
"mujoco",
"runner_crl_4"
],
"command_line": "--algo=APPO --with_wandb=True --wandb_tags mujoco runner_crl_4 --seed=4444 --env=mujoco_halfcheetah --experiment=17_mujoco_all_envs_see_4444_env_mujoco_halfcheetah --train_dir=./train_dir --experiments_root=mujoco_all_envs/mujoco_all_envs_crl_4",
"cli_args": {
"algo": "APPO",
"env": "mujoco_halfcheetah",
"experiment": "17_mujoco_all_envs_see_4444_env_mujoco_halfcheetah",
"train_dir": "./train_dir",
"experiments_root": "mujoco_all_envs/mujoco_all_envs_crl_4",
"seed": 4444,
"with_wandb": true,
"wandb_tags": [
"mujoco",
"runner_crl_4"
]
},
"git_hash": "4e69a02b57fff18dbbf96054866d0d759f70c5fa",
"git_repo_name": "https://github.com/andrewzhang505/sample-factory.git"
}