Upload folder using huggingface_hub

factor_sweeps/demon_attack/context_window/train/factor_sweep:demon_attack:frame_stack:uniform_u2_6:fs10:obs15:stride4:seed14/checkpoint_p0/best_000046560_23838720_reward_13124.950.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7e25bdad1aa41adf17f899857031c00aee8744f5afc73c59df4f80ea9278bd
+size 21547577

factor_sweeps/demon_attack/context_window/train/factor_sweep:demon_attack:frame_stack:uniform_u2_6:fs10:obs15:stride4:seed14/checkpoint_p0/checkpoint_000017536_8978432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3affc2df3f7aa8ca07e12f80de3e8a2542ff263869aed9e58609f8b0e551eba8
+size 21547937

factor_sweeps/demon_attack/context_window/train/factor_sweep:demon_attack:frame_stack:uniform_u2_6:fs10:obs15:stride4:seed14/checkpoint_p0/checkpoint_000031936_16351232.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c92ae35f57b6f7dd383c736f22951c5fa3d4059037dbe4ab7a5e86603801329
+size 21547937

factor_sweeps/demon_attack/context_window/train/factor_sweep:demon_attack:frame_stack:uniform_u2_6:fs10:obs15:stride4:seed14/checkpoint_p0/checkpoint_000047232_24182784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7125d6062812f9733619234cd0d671a77ed899eddc8d6a0d45c623ddd80b6dc7
+size 21547937

factor_sweeps/demon_attack/context_window/train/factor_sweep:demon_attack:frame_stack:uniform_u2_6:fs10:obs15:stride4:seed14/checkpoint_p0/checkpoint_000048864_25018368.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99b895f0a278208ec49f47db2747b484dedaf98de87ee6e864fc53743b472b5
+size 21547937

factor_sweeps/demon_attack/context_window/train/factor_sweep:demon_attack:frame_stack:uniform_u2_6:fs10:obs15:stride4:seed14/checkpoint_p0/checkpoint_000048880_25026560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ae89909b6589fd21baf75b115dbb3d76230ffa55b2b3692be325395d63f963
+size 21547937

factor_sweeps/demon_attack/context_window/train/factor_sweep:demon_attack:frame_stack:uniform_u2_6:fs10:obs15:stride4:seed14/config.json

@@ -0,0 +1,255 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "latency_demon_attack",
+  "experiment": "demon_attack_frame_stack_uniform_u2_6_fs10_seed14",
+  "train_dir": "results/checkpoints_factor_sweeps/demon_attack/context_window",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": 14,
+  "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": 300,
+  "num_workers": 1,
+  "num_envs_per_worker": 1,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 2,
+  "rollout": 64,
+  "recurrence": 32,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1.0,
+  "reward_clip": 1000.0,
+  "value_bootstrap": false,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.003,
+  "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": 0.2,
+  "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": 0.000303,
+  "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": 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": 1,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": true,
+  "heartbeat_interval": 20,
+  "heartbeat_reporting_interval": 180,
+  "train_for_env_steps": 25000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 600,
+  "keep_checkpoints": 5,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": -1,
+  "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": "elu",
+  "policy_initialization": "orthogonal",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": true,
+  "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": "latency-sensitive-bench",
+  "wandb_group": "demon-attack-fs10-uniform_u2_6",
+  "wandb_job_type": "sample_factory",
+  "wandb_tags": [
+    "factor_sweep",
+    "demon-attack",
+    "frame_stack",
+    "uniform",
+    "uniform_u2_6",
+    "fs10",
+    "seed14"
+  ],
+  "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_id": "ALE/DemonAttack-v5",
+  "env_fps": 60.0,
+  "obs_fps": 15.0,
+  "screen_size": 84,
+  "noop_max": 30,
+  "frame_stack": 10,
+  "terminal_on_life_loss": true,
+  "clip_reward": true,
+  "repeat_action_probability": 0.0,
+  "full_action_space": false,
+  "max_episode_steps": 25000,
+  "simulator": "gpu",
+  "gpu_env_device": "auto",
+  "gpu_env_batch_size": 512,
+  "export_env_raw_rgb_frames": false,
+  "mode": "train",
+  "latency_type": "uniform_distribution",
+  "fixed_latency_ms": null,
+  "mean_latency_ms": null,
+  "std_latency_ms": null,
+  "min_latency_ms": 33.333333333333336,
+  "max_latency_ms": 100.0,
+  "latency_seed": 14,
+  "add_latency_info": false,
+  "max_pending_actions": null,
+  "hold_policy": "hold",
+  "ordering_policy": "latest_ready",
+  "eval_episodes": 100,
+  "eval_parallel_envs": 100,
+  "eval_latency_raw_frame_values": "0,1,2,3,4,5",
+  "eval_max_steps": 36000,
+  "eval_deterministic": true,
+  "eval_raw_reward": true,
+  "episode_metrics_path": "results/checkpoints_factor_sweeps/demon_attack/context_window/demon_attack_frame_stack_uniform_u2_6_fs10_seed14/episode_metrics.jsonl",
+  "command_line": "--mode train --algo APPO --env latency_demon_attack --experiment demon_attack_frame_stack_uniform_u2_6_fs10_seed14 --train_dir results/checkpoints_factor_sweeps/demon_attack/context_window --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-env-batch-size 512 --seed 14 --episode_metrics_path results/checkpoints_factor_sweeps/demon_attack/context_window/demon_attack_frame_stack_uniform_u2_6_fs10_seed14/episode_metrics.jsonl --train_for_env_steps 25000000 --num_workers 1 --num_envs_per_worker 1 --num_policies 1 --batch_size 1024 --rollout 64 --recurrence 32 --num_epochs 2 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 300 --learning_rate 0.000303 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --value_loss_coeff 0.5 --max_grad_norm 0.0 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --batched_sampling True --use_rnn False --normalize_returns True --normalize_input True --latency-type uniform_distribution --min-latency-ms 33.333333333333336 --max-latency-ms 100.0 --latency-seed 14 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 100 --eval-max-steps 36000 --eval-deterministic True --eval-raw-reward --with_wandb True --wandb_project latency-sensitive-bench --wandb_group demon-attack-fs10-uniform_u2_6 --wandb_job_type sample_factory --wandb_tags factor_sweep demon-attack frame_stack uniform uniform_u2_6 fs10 seed14 --env_id ALE/DemonAttack-v5 --env-fps 60 --obs-fps 15.0 --screen_size 84 --noop_max 30 --frame_stack 10 --terminal_on_life_loss True --clip_reward True --repeat_action_probability 0.0 --full_action_space False --max_episode_steps 25000 --simulator gpu --gpu-env-device auto --hold-policy hold --ordering-policy latest_ready",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "latency_demon_attack",
+    "experiment": "demon_attack_frame_stack_uniform_u2_6_fs10_seed14",
+    "train_dir": "results/checkpoints_factor_sweeps/demon_attack/context_window",
+    "restart_behavior": "resume",
+    "device": "gpu",
+    "seed": 14,
+    "num_policies": 1,
+    "async_rl": true,
+    "batched_sampling": true,
+    "worker_num_splits": 1,
+    "max_policy_lag": 300,
+    "num_workers": 1,
+    "num_envs_per_worker": 1,
+    "batch_size": 1024,
+    "num_batches_per_epoch": 8,
+    "num_epochs": 2,
+    "rollout": 64,
+    "recurrence": 32,
+    "gamma": 0.99,
+    "normalize_returns": true,
+    "value_loss_coeff": 0.5,
+    "gae_lambda": 0.95,
+    "ppo_clip_ratio": 0.1,
+    "ppo_clip_value": 0.2,
+    "max_grad_norm": 0.0,
+    "learning_rate": 0.000303,
+    "normalize_input": true,
+    "actor_worker_gpus": [
+      0
+    ],
+    "experiment_summaries_interval": 1,
+    "stats_avg": 100,
+    "train_for_env_steps": 25000000,
+    "save_every_sec": 600,
+    "keep_checkpoints": 5,
+    "use_rnn": false,
+    "env_gpu_actions": true,
+    "env_gpu_observations": true,
+    "with_wandb": true,
+    "wandb_project": "latency-sensitive-bench",
+    "wandb_group": "demon-attack-fs10-uniform_u2_6",
+    "wandb_job_type": "sample_factory",
+    "wandb_tags": [
+      "factor_sweep",
+      "demon-attack",
+      "frame_stack",
+      "uniform",
+      "uniform_u2_6",
+      "fs10",
+      "seed14"
+    ],
+    "env_id": "ALE/DemonAttack-v5",
+    "env_fps": 60.0,
+    "obs_fps": 15.0,
+    "screen_size": 84,
+    "noop_max": 30,
+    "frame_stack": 10,
+    "terminal_on_life_loss": true,
+    "clip_reward": true,
+    "repeat_action_probability": 0.0,
+    "full_action_space": false,
+    "max_episode_steps": 25000,
+    "simulator": "gpu",
+    "gpu_env_device": "auto",
+    "gpu_env_batch_size": 512,
+    "mode": "train",
+    "latency_type": "uniform_distribution",
+    "min_latency_ms": 33.333333333333336,
+    "max_latency_ms": 100.0,
+    "latency_seed": 14,
+    "add_latency_info": false,
+    "hold_policy": "hold",
+    "ordering_policy": "latest_ready",
+    "eval_episodes": 100,
+    "eval_parallel_envs": 100,
+    "eval_max_steps": 36000,
+    "eval_deterministic": true,
+    "eval_raw_reward": true,
+    "episode_metrics_path": "results/checkpoints_factor_sweeps/demon_attack/context_window/demon_attack_frame_stack_uniform_u2_6_fs10_seed14/episode_metrics.jsonl"
+  },
+  "git_hash": "eb3a2e1efbd2aa03a60d7f44f5e18d8fdd0f5a2d",
+  "git_repo_name": "git@github.com:ZihanWang314/latency-sensitive-bench.git",
+  "eval_env_frameskip": 1,
+  "output_dir": "outputs/factor_sweeps/demon_attack/context_window/train/frame_stack/uniform_u2_6/fs10/seed_14",
+  "wandb_unique_id": "demon-attack-fs10-uniform_u2_6-s14"
+}

factor_sweeps/demon_attack/context_window/train/factor_sweep:demon_attack:frame_stack:uniform_u2_6:fs10:obs15:stride4:seed14/git.diff

@@ -0,0 +1,7 @@
+diff --git a/starVLA b/starVLA
+index ab3380d..9d8c567 160000
+--- a/starVLA
++++ b/starVLA
+@@ -1 +1 @@
+-Subproject commit ab3380dfbd1de9649c15d154cc41b97788674537
++Subproject commit 9d8c567188a3aa2a825296016cf17f3977101d8f