Upload folder using huggingface_hub

.gitattributes

@@ -48,3 +48,4 @@ factor_sweeps/flappy/observation_stride/train/factor_sweep:flappy:observation_st
 factor_sweeps/flappy/observation_stride/train/factor_sweep:flappy:observation_stride:fixed_l2:fs4:obs15:stride2:seed12/episode_metrics.jsonl filter=lfs diff=lfs merge=lfs -text
 factor_sweeps/flappy/context_window/train/factor_sweep:flappy:frame_stack:fixed_l2:fs5:obs30:stride1:seed10/episode_metrics.jsonl filter=lfs diff=lfs merge=lfs -text
 factor_sweeps/flappy/context_window/train/factor_sweep:flappy:frame_stack:fixed_l2:fs5:obs30:stride1:seed11/episode_metrics.jsonl filter=lfs diff=lfs merge=lfs -text
+factor_sweeps/flappy/context_window/train/factor_sweep:flappy:frame_stack:fixed_l2:fs5:obs30:stride1:seed12/episode_metrics.jsonl filter=lfs diff=lfs merge=lfs -text

factor_sweeps/flappy/context_window/train/factor_sweep:flappy:frame_stack:fixed_l2:fs5:obs30:stride1:seed12/checkpoint_p0/best_000048840_25034752_reward_2156.198.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881450007cfa014c9d46bbf821d36d207882ccbc3953672f02e06298a21abe2a
+size 22210361

factor_sweeps/flappy/context_window/train/factor_sweep:flappy:frame_stack:fixed_l2:fs5:obs30:stride1:seed12/checkpoint_p0/checkpoint_000021152_10846208.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1401620a4db490f3e59bb22706fd389deb0273a8e6ea08d7e14cdf932072aba
+size 22210721

factor_sweeps/flappy/context_window/train/factor_sweep:flappy:frame_stack:fixed_l2:fs5:obs30:stride1:seed12/checkpoint_p0/checkpoint_000042720_21889024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f62bc7349347379d1899dafd39c31f488b9037411282d6f3a0d23b54890f297
+size 22210721

factor_sweeps/flappy/context_window/train/factor_sweep:flappy:frame_stack:fixed_l2:fs5:obs30:stride1:seed12/checkpoint_p0/checkpoint_000048840_25034752.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e80d5d6d07bced0410b185491cb4288b7fd087a616e3372f6beca2a24e0a8e6
+size 22210721

factor_sweeps/flappy/context_window/train/factor_sweep:flappy:frame_stack:fixed_l2:fs5:obs30:stride1:seed12/config.json

@@ -0,0 +1,266 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "latency_flappy",
+  "experiment": "flappy_frame_stack_fixed_l2_fs5_seed12",
+  "train_dir": "results/checkpoints_factor_sweeps/flappy/context_window",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": 12,
+  "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": 400,
+  "num_workers": 2,
+  "num_envs_per_worker": 1,
+  "batch_size": 4096,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 8,
+  "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": 0.003,
+  "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": 0.5,
+  "learning_rate": 0.00025,
+  "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": "flappy-fs5-fixed_l2",
+  "wandb_job_type": "sample_factory",
+  "wandb_tags": [
+    "factor_sweep",
+    "flappy",
+    "frame_stack",
+    "fixed",
+    "fixed_l2",
+    "fs5",
+    "seed12"
+  ],
+  "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,
+  "gym_id": "FlappyBird-v0",
+  "env_fps": 30.0,
+  "obs_fps": 30.0,
+  "use_lidar": false,
+  "normalize_obs": true,
+  "audio_on": false,
+  "screen_size": "",
+  "obs_resize": "84,84",
+  "use_gpu_render": true,
+  "simulator": "gpu",
+  "gpu_render_device": "auto",
+  "gpu_render_batch_size": 128,
+  "gpu_render_profile": false,
+  "gpu_render_profile_interval": 200,
+  "pipe_gap": 100,
+  "bird_color": "yellow",
+  "pipe_color": "green",
+  "background": "day",
+  "score_limit": -1,
+  "frame_stack": 5,
+  "debug": false,
+  "debug_timelimit_diagnostics": false,
+  "max_episode_steps": 0,
+  "mode": "train",
+  "latency_type": "fixed",
+  "fixed_latency_ms": 66.66666666666667,
+  "mean_latency_ms": null,
+  "std_latency_ms": null,
+  "min_latency_ms": null,
+  "max_latency_ms": null,
+  "latency_seed": null,
+  "add_latency_info": false,
+  "max_pending_actions": null,
+  "hold_policy": "one_frame_then_noop",
+  "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": 3600,
+  "eval_deterministic": true,
+  "eval_raw_reward": false,
+  "episode_metrics_path": "results/checkpoints_factor_sweeps/flappy/context_window/flappy_frame_stack_fixed_l2_fs5_seed12/episode_metrics.jsonl",
+  "command_line": "--mode train --algo APPO --env latency_flappy --experiment flappy_frame_stack_fixed_l2_fs5_seed12 --train_dir results/checkpoints_factor_sweeps/flappy/context_window --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-render-batch-size 128 --seed 12 --episode_metrics_path results/checkpoints_factor_sweeps/flappy/context_window/flappy_frame_stack_fixed_l2_fs5_seed12/episode_metrics.jsonl --train_for_env_steps 25000000 --num_workers 2 --num_envs_per_worker 1 --num_policies 1 --batch_size 4096 --rollout 128 --recurrence 1 --num_epochs 8 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 400 --learning_rate 0.00025 --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 0.5 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --use_rnn False --normalize_returns True --normalize_input True --latency-type fixed --fixed-latency-ms 66.66666666666667 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 100 --eval-max-steps 3600 --eval-deterministic True --with_wandb True --wandb_project latency-sensitive-bench --wandb_group flappy-fs5-fixed_l2 --wandb_job_type sample_factory --wandb_tags factor_sweep flappy frame_stack fixed fixed_l2 fs5 seed12 --gym_id FlappyBird-v0 --env-fps 30 --obs-fps 30.0 --use_lidar False --normalize_obs True --audio_on False --obs_resize 84,84 --use-gpu-render True --simulator gpu --gpu-render-device auto --gpu-render-profile False --gpu-render-profile-interval 200 --pipe_gap 100 --bird_color yellow --pipe_color green --background day --frame_stack 5 --debug False --debug-timelimit-diagnostics False --hold-policy one_frame_then_noop --ordering-policy latest_ready",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "latency_flappy",
+    "experiment": "flappy_frame_stack_fixed_l2_fs5_seed12",
+    "train_dir": "results/checkpoints_factor_sweeps/flappy/context_window",
+    "restart_behavior": "resume",
+    "device": "gpu",
+    "seed": 12,
+    "num_policies": 1,
+    "async_rl": true,
+    "batched_sampling": true,
+    "worker_num_splits": 1,
+    "max_policy_lag": 400,
+    "num_workers": 2,
+    "num_envs_per_worker": 1,
+    "batch_size": 4096,
+    "num_batches_per_epoch": 8,
+    "num_epochs": 8,
+    "rollout": 128,
+    "recurrence": 1,
+    "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": 0.5,
+    "learning_rate": 0.00025,
+    "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": "flappy-fs5-fixed_l2",
+    "wandb_job_type": "sample_factory",
+    "wandb_tags": [
+      "factor_sweep",
+      "flappy",
+      "frame_stack",
+      "fixed",
+      "fixed_l2",
+      "fs5",
+      "seed12"
+    ],
+    "gym_id": "FlappyBird-v0",
+    "env_fps": 30.0,
+    "obs_fps": 30.0,
+    "use_lidar": false,
+    "normalize_obs": true,
+    "audio_on": false,
+    "obs_resize": "84,84",
+    "use_gpu_render": true,
+    "simulator": "gpu",
+    "gpu_render_device": "auto",
+    "gpu_render_batch_size": 128,
+    "gpu_render_profile": false,
+    "gpu_render_profile_interval": 200,
+    "pipe_gap": 100,
+    "bird_color": "yellow",
+    "pipe_color": "green",
+    "background": "day",
+    "frame_stack": 5,
+    "debug": false,
+    "debug_timelimit_diagnostics": false,
+    "mode": "train",
+    "latency_type": "fixed",
+    "fixed_latency_ms": 66.66666666666667,
+    "add_latency_info": false,
+    "hold_policy": "one_frame_then_noop",
+    "ordering_policy": "latest_ready",
+    "eval_episodes": 100,
+    "eval_parallel_envs": 100,
+    "eval_max_steps": 3600,
+    "eval_deterministic": true,
+    "episode_metrics_path": "results/checkpoints_factor_sweeps/flappy/context_window/flappy_frame_stack_fixed_l2_fs5_seed12/episode_metrics.jsonl"
+  },
+  "git_hash": "284fe8ace24f0e8a40c03c5b559969abd7caeb29",
+  "git_repo_name": "git@github.com:ZihanWang314/latency-sensitive-bench.git",
+  "eval_env_frameskip": 1,
+  "output_dir": "outputs/factor_sweeps/flappy/context_window/train/frame_stack/fixed_l2/fs5/seed_12",
+  "wandb_unique_id": "flappy-fs5-fixed_l2-s12"
+}

factor_sweeps/flappy/context_window/train/factor_sweep:flappy:frame_stack:fixed_l2:fs5:obs30:stride1:seed12/episode_metrics.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56af456ed3e58ad4937015279dbdba3f55d22410fafdc5225a0018df74f34a5
+size 20384405