Upload folder using huggingface_hub

.gitattributes

@@ -2,7 +2,6 @@
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
@@ -25,7 +24,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1666554178.r12i0n7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d6690167305d19adae5a1910c49cce96aab0dc3bf34b2374b061abe3368430
+size 9192848

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 9.06 +/- 5.41
+      value: 19.69 +/- 3.66
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000466273_3819708416_reward_63.056.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f546634a38180cb4a57aec199213e3b845b90a5ebb8206ddaa081c2c9d4ba854
+size 41231900

checkpoint_p0/checkpoint_000538763_4413546496.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dae22eea622f39a8ea7e51fa52eed63489f4548785a8c2c80d9fc5b1bc676b
+size 41231900

checkpoint_p0/checkpoint_000539850_4422451200.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73fcca08938df3021096188ffa087fe10baadc4365972130f8958a74df3e498f
+size 41231900

config.json

@@ -2,11 +2,11 @@
   "help": false,
   "algo": "APPO",
   "env": "doom_health_gathering_supreme",
-  "experiment": "default_experiment",
+  "experiment": "doom_health_gathering_supreme_2222",
   "train_dir": "/content/train_dir",
   "restart_behavior": "resume",
   "device": "gpu",
-  "seed": null,
+  "seed": 2222,
   "num_policies": 1,
   "async_rl": true,
   "serial_mode": false,
@@ -15,9 +15,9 @@
   "worker_num_splits": 2,
   "policy_workers_per_policy": 1,
   "max_policy_lag": 1000,
-  "num_workers": 8,
-  "num_envs_per_worker": 4,
-  "batch_size": 1024,
+  "num_workers": 20,
+  "num_envs_per_worker": 12,
+  "batch_size": 2048,
   "num_batches_per_epoch": 1,
   "num_epochs": 1,
   "rollout": 32,
@@ -42,17 +42,15 @@
   "adam_eps": 1e-06,
   "adam_beta1": 0.9,
   "adam_beta2": 0.999,
-  "max_grad_norm": 4.0,
+  "max_grad_norm": 0.0,
   "learning_rate": 0.0001,
   "lr_schedule": "constant",
   "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_experience_max_seconds": 1,
   "decorrelate_envs_on_one_worker": true,
   "actor_worker_gpus": [],
   "set_workers_cpu_affinity": true,
@@ -63,10 +61,10 @@
   "flush_summaries_interval": 30,
   "stats_avg": 100,
   "summaries_use_frameskip": true,
-  "heartbeat_interval": 20,
-  "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 4000000,
-  "train_for_seconds": 10000000000,
+  "heartbeat_interval": 10,
+  "heartbeat_reporting_interval": 300,
+  "train_for_env_steps": 10000000000,
+  "train_for_seconds": 3600000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,
   "load_checkpoint_kind": "latest",
@@ -85,10 +83,10 @@
   ],
   "use_rnn": true,
   "rnn_size": 512,
-  "rnn_type": "gru",
+  "rnn_type": "lstm",
   "rnn_num_layers": 1,
   "decoder_mlp_layers": [],
-  "nonlinearity": "elu",
+  "nonlinearity": "relu",
   "policy_initialization": "orthogonal",
   "policy_init_gain": 1.0,
   "actor_critic_share_weights": true,
@@ -97,7 +95,6 @@
   "initial_stddev": 1.0,
   "use_env_info_cache": false,
   "env_gpu_actions": false,
-  "env_gpu_observations": true,
   "env_frameskip": 4,
   "env_framestack": 1,
   "pixel_format": "CHW",
@@ -130,13 +127,30 @@
   "wide_aspect_ratio": false,
   "eval_env_frameskip": 1,
   "fps": 35,
-  "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
+  "command_line": "--train_for_seconds=3600000 --algo=APPO --gamma=0.99 --use_rnn=True --num_workers=20 --num_envs_per_worker=12 --num_epochs=1 --rollout=32 --recurrence=32 --batch_size=2048 --benchmark=False --max_grad_norm=0.0 --decorrelate_experience_max_seconds=1 --nonlinearity=relu --rnn_type=lstm --num_policies=1 --heartbeat_reporting_interval=300 --train_dir=/scratch/sample_factory/train_dir/vizdoom --seed=2222 --experiment=vizdoom_doom_health_gathering_supreme_2222 --env=doom_health_gathering_supreme",
   "cli_args": {
+    "algo": "APPO",
     "env": "doom_health_gathering_supreme",
-    "num_workers": 8,
-    "num_envs_per_worker": 4,
-    "train_for_env_steps": 4000000
+    "experiment": "doom_health_gathering_supreme_2222",
+    "train_dir": "/content/train_dir/",
+    "seed": 2222,
+    "num_policies": 1,
+    "num_workers": 20,
+    "num_envs_per_worker": 12,
+    "batch_size": 2048,
+    "num_epochs": 1,
+    "rollout": 32,
+    "recurrence": 32,
+    "gamma": 0.99,
+    "max_grad_norm": 0.0,
+    "decorrelate_experience_max_seconds": 1,
+    "heartbeat_reporting_interval": 300,
+    "train_for_seconds": 3600000,
+    "benchmark": false,
+    "use_rnn": true,
+    "rnn_type": "lstm",
+    "nonlinearity": "relu"
   },
-  "git_hash": "unknown",
-  "git_repo_name": "not a git repository"
+  "git_hash": "9da68b57eecd73c3c884c1be2d938b46aa7a7f49",
+  "git_repo_name": "https://github.com/alex-petrenko/sample-factory.git"
 }

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ebcabbea4ab6a1cc5f2b9af3b57a34e73ee6ed04914aa0ea98c5d599f686ffa
-size 17136331
+oid sha256:5c9473e3a855ff1f32cfa3068fbc9499f3d66699445301a8717c095a60dba214
+size 39444727