Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1690158571.11c477af595d

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94bdd879a0109762a6cdce9f2e0535de8e3a847021c27826bcc9087681342db4
+size 40

.summary/0/events.out.tfevents.1690158643.11c477af595d

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5aa61c110fc96828e2193a122bc9b3f85b850078d4a7f2ee4e245f74611004
+size 7843

.summary/0/events.out.tfevents.1690158742.11c477af595d

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e658e58317575cacbd3230ed870ab315919aee4c2a34fcd6fc2c10836b52ea48
+size 2892

.summary/0/events.out.tfevents.1690158839.11c477af595d

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6861b6836287aae2917b58af3c158bd6df11fe2f2a33b04f583f20bc94e4811
+size 2683560

README.md

@@ -11,16 +11,16 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: doom_health_gathering_supreme
-      type: doom_health_gathering_supreme
+      name: doom_deathmatch_bots
+      type: doom_deathmatch_bots
     metrics:
     - type: mean_reward
-      value: 10.63 +/- 4.17
+      value: 1.30 +/- 1.19
       name: mean_reward
       verified: false
 ---
 
-A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
+A(n) **APPO** model trained on the **doom_deathmatch_bots** environment.
 
 This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
 Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
@@ -38,7 +38,7 @@ python -m sample_factory.huggingface.load_from_hub -r Corianas/rl_course_vizdoom
 
 To run the model after download, use the `enjoy` script corresponding to this environment:
 ```
-python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
+python -m <path.to.enjoy.module> --algo=APPO --env=doom_deathmatch_bots --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
 ```
 
 
@@ -49,7 +49,7 @@ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
 
 To continue training with this model, use the `train` script corresponding to this environment:
 ```
-python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
+python -m <path.to.train.module> --algo=APPO --env=doom_deathmatch_bots --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
 ```
 
 Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.

checkpoint_p0/best_000000113_462848_reward_-2.703.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e88113be823414a8311235c15b73430b2f41d16243287a51240c23adf5f7e5c
+size 37738579

checkpoint_p0/checkpoint_000001447_5926912.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b5c86642735e6433da16ab7fb21e48dac02e50a08dac04883ed44e784fc1a7
+size 37739171

checkpoint_p0/checkpoint_000001466_6004736.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb4516467a6224e401ab39da7d7d9a71c41a31e5fef902181c861b1f293990c
+size 37739171

config.json

@@ -1,7 +1,7 @@
 {
   "help": false,
   "algo": "APPO",
-  "env": "doom_health_gathering_supreme",
+  "env": "doom_deathmatch_bots",
   "experiment": "default_experiment",
   "train_dir": "/content/train_dir",
   "restart_behavior": "resume",
@@ -16,7 +16,7 @@
   "policy_workers_per_policy": 1,
   "max_policy_lag": 1000,
   "num_workers": 8,
-  "num_envs_per_worker": 16,
+  "num_envs_per_worker": 8,
   "batch_size": 1024,
   "num_batches_per_epoch": 1,
   "num_epochs": 1,
@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 10000000,
+  "train_for_env_steps": 6000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,
@@ -99,7 +99,7 @@
   "env_gpu_actions": false,
   "env_gpu_observations": true,
   "env_frameskip": 4,
-  "env_framestack": 1,
+  "env_framestack": 3,
   "pixel_format": "CHW",
   "use_record_episode_statistics": false,
   "with_wandb": false,
@@ -130,12 +130,12 @@
   "wide_aspect_ratio": false,
   "eval_env_frameskip": 1,
   "fps": 35,
-  "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=16 --train_for_env_steps=10000000",
+  "command_line": "--env=doom_deathmatch_bots --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
   "cli_args": {
-    "env": "doom_health_gathering_supreme",
+    "env": "doom_deathmatch_bots",
     "num_workers": 8,
-    "num_envs_per_worker": 16,
-    "train_for_env_steps": 10000000
+    "num_envs_per_worker": 4,
+    "train_for_env_steps": 4000000
   },
   "git_hash": "unknown",
   "git_repo_name": "not a git repository"

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f49492774bb510c377074283591b69af26a436d360cab2c81c19cc1637a264e
-size 20549457
+oid sha256:458e608759cca0c76d1dcf6ada7e3cadcc9d4f67952c47026958bd8d426c3b9d
+size 144308102