| { | |
| "help": false, | |
| "algo": "APPO", | |
| "env": "atari_pong", | |
| "experiment": "atari_pong_APPO", | |
| "train_dir": "./train_atari", | |
| "restart_behavior": "restart", | |
| "device": "gpu", | |
| "seed": 1234, | |
| "num_policies": 2, | |
| "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": 16, | |
| "num_envs_per_worker": 2, | |
| "batch_size": 1024, | |
| "num_batches_per_epoch": 8, | |
| "num_epochs": 4, | |
| "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": 0.0004677351413, | |
| "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, | |
| "lr_adaptive_min": 1e-06, | |
| "lr_adaptive_max": 0.01, | |
| "obs_subtract_mean": 0.0, | |
| "obs_scale": 255.0, | |
| "normalize_input": true, | |
| "normalize_input_keys": [ | |
| "obs" | |
| ], | |
| "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, | |
| "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": 100000000, | |
| "train_for_seconds": 10000000000, | |
| "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_gpu_observations": true, | |
| "env_frameskip": 4, | |
| "env_framestack": 4, | |
| "pixel_format": "CHW", | |
| "use_record_episode_statistics": true, | |
| "with_wandb": true, | |
| "wandb_user": "matt-stammers", | |
| "wandb_project": "atari_APPO", | |
| "wandb_group": "atari_pong", | |
| "wandb_job_type": "SF", | |
| "wandb_tags": [ | |
| "atari" | |
| ], | |
| "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, | |
| "command_line": "--algo=APPO --env=atari_pong --experiment=atari_pong_APPO --num_policies=2 --restart_behavior=restart --train_dir=./train_atari --train_for_env_steps=100000000 --seed=1234 --num_workers=16 --num_envs_per_worker=2 --num_batches_per_epoch=8 --async_rl=true --batched_sampling=true --batch_size=1024 --max_grad_norm=0 --learning_rate=0.0003033891184 --heartbeat_interval=10 --heartbeat_reporting_interval=60 --save_milestones_sec=1200 --num_epochs=4 --exploration_loss_coeff=0.0004677351413 --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari_APPO --wandb_group=atari_pong --wandb_job_type=SF --wandb_tags=atari", | |
| "cli_args": { | |
| "algo": "APPO", | |
| "env": "atari_pong", | |
| "experiment": "atari_pong_APPO", | |
| "train_dir": "./train_atari", | |
| "restart_behavior": "restart", | |
| "seed": 1234, | |
| "num_policies": 2, | |
| "async_rl": true, | |
| "batched_sampling": true, | |
| "num_workers": 16, | |
| "num_envs_per_worker": 2, | |
| "batch_size": 1024, | |
| "num_batches_per_epoch": 8, | |
| "num_epochs": 4, | |
| "exploration_loss_coeff": 0.0004677351413, | |
| "max_grad_norm": 0.0, | |
| "learning_rate": 0.0003033891184, | |
| "heartbeat_interval": 10, | |
| "heartbeat_reporting_interval": 60, | |
| "train_for_env_steps": 100000000, | |
| "save_milestones_sec": 1200, | |
| "with_wandb": true, | |
| "wandb_user": "matt-stammers", | |
| "wandb_project": "atari_APPO", | |
| "wandb_group": "atari_pong", | |
| "wandb_job_type": "SF", | |
| "wandb_tags": [ | |
| "atari" | |
| ] | |
| }, | |
| "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e", | |
| "git_repo_name": "not a git repository", | |
| "wandb_unique_id": "atari_pong_APPO_20231014_010121_934395" | |
| } |