Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1696952033.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f976fb552b531281672660e211d0ff451771da935d46dc5ab73f81f3ea2bea
+size 7554267

.summary/1/events.out.tfevents.1696952033.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef3874c4faef5050e91f986c3c9b0f6f0cd6ef2119ce4210048474c733fe064
+size 4383104

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_demonattack
     metrics:
     - type: mean_reward
-      value: 3140.50 +/- 1778.95
+      value: 109507.00 +/- 2714.30
       name: mean_reward
       verified: false
 ---
@@ -30,15 +30,128 @@ Documentation for how to use Sample-Factory can be found at https://www.samplefa
 
 After installing Sample-Factory, download the model with:
 ```
-python -m sample_factory.huggingface.load_from_hub -r MattStammers/appo-atari_demonattack
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_demonattack
 ```
 
     
+## About the Model
+
+This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it. 
+
+The aim is to reach state-of-the-art (SOTA) performance on each atari environment. I will flag the models with SOTA when they reach at or near these levels. 
+
+The hyperparameters used in the model are the ones I have pushed to my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his.
+I saved time and energy by using many of his tuned hyperparameters to maximise performance. However, he used 2 billion training steps. I have started as explained above at 10 million then moved to 100m to see how performance goes:
+```
+hyperparameters =  {
+  "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,
+  }
+
+  ```
+
+
+    
 ## Using the model
 
 To run the model after download, use the `enjoy` script corresponding to this environment:
 ```
-python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_demonattack --train_dir=./train_dir --experiment=appo-atari_demonattack
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_demonattack --train_dir=./train_dir --experiment=APPO-atari_demonattack
 ```
 
 
@@ -49,7 +162,7 @@ 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 sf_examples.atari.train_atari --algo=APPO --env=atari_demonattack --train_dir=./train_dir --experiment=appo-atari_demonattack --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_demonattack --train_dir=./train_dir --experiment=APPO-atari_demonattack --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_000084160_86179840_reward_124.660.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c7ec835895e15606d9ddedeaff980bcf4811f70d06c227762914fea988cc1d
+size 20721843

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd58bf58ae00acb7af441bfe0f7e9502cae1dbac1f68e2cbe7ff7b913f8c5107
+size 20722179

checkpoint_p0/checkpoint_000097792_100139008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c014e1f97dba05a7437d757a810e93fbfb0a8b2029ed3ceb31a27e6536ece0
+size 20722179

checkpoint_p0/milestones/checkpoint_000008352_8552448.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0fe50b7484c441ab4248dda81c9c7a5aa3c1517f897a87d25dede25ede0117c
+size 20723035

checkpoint_p0/milestones/checkpoint_000016864_17268736.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e671ef62c6166161e3993fed1fee0b1e93559e37063ea350139586d86311add
+size 20723091

checkpoint_p0/milestones/checkpoint_000025376_25985024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1fba863f940f778d87da1033aec1e8bf31455cc4bf8279ce3b0e00a738cc315
+size 20723091

checkpoint_p0/milestones/checkpoint_000033888_34701312.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d501f94352d51f5956b39c7f888cf2371ee7392b673aefd6ef3d70209b82b61
+size 20723091

checkpoint_p0/milestones/checkpoint_000042400_43417600.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2036013eee02313d50ea155a5d1de4e34e1fa0ee6b001e073083dc3a6fbb2e2c
+size 20723091

checkpoint_p0/milestones/checkpoint_000050880_52101120.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbbab1f36f3aed5940cb361641ff2dab83a30f36d07d2deb6709b1d09536ffa1
+size 20723091

checkpoint_p0/milestones/checkpoint_000059392_60817408.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fedb5be9b28c1f23c642486ae73b1d77b15c58f11b0b794e1a8a091c171d9b27
+size 20723091

checkpoint_p0/milestones/checkpoint_000067872_69500928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d188b1039970aa2962ef841fed7a6c4de34d29b4f663529a58ee3057c8623a
+size 20723091

checkpoint_p0/milestones/checkpoint_000076384_78217216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0007b71ed04862ccb850520ed121c66db633da5da3b26b3d40e863a4e5204080
+size 20723091

checkpoint_p0/milestones/checkpoint_000084896_86933504.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33aa46a1b076425448ce653cc832ebc6661fdcbcf7b2ae90215fdd7de37d24d
+size 20723091

checkpoint_p0/milestones/checkpoint_000093408_95649792.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5deebd8bf81c863a9c1a908ee270cb66897123139ffb4b45b6e2a5633d59d303
+size 20723091

checkpoint_p1/best_000089504_91652096_reward_123.000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7525f705c64fbf15cb7fe449de54aab5be7bf7bd141e13887de94741c02f678
+size 20721843

checkpoint_p1/checkpoint_000097568_99909632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac33dd6f4d7e5fdf8c24d5a346a453f9f8b00bcf9444a47c05c96b0575043e1
+size 20722179

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb4719cc8b099dc0615910d480d5295654079326a1e0bd139f1d9cff5090c14
+size 20722179

checkpoint_p1/milestones/checkpoint_000008320_8519680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16cdf124c398b913e8ce23b7427dbbec3133f5802a270d7fcd79721b04e3d264
+size 20723035

checkpoint_p1/milestones/checkpoint_000016832_17235968.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f340a4f0538416fc4e82c7aebef018a84c1228d54cd2d118946f98771d6255e1
+size 20723091

checkpoint_p1/milestones/checkpoint_000025344_25952256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5269d77360044869b91214b5c3a4be0c4cbdc3a8306c3d8e9b00722ead7804e0
+size 20723091

checkpoint_p1/milestones/checkpoint_000033792_34603008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c501fa2e4f2dc7be0fd5032f76c5cdc01fd76e65b3417705d5f22e227b5df96
+size 20723091

checkpoint_p1/milestones/checkpoint_000042304_43319296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91bd4aa9b0cc4d41a31fcee5cd3ab8e4ba72092f21ad0ed8d5a3ae24ecce1427
+size 20723091

checkpoint_p1/milestones/checkpoint_000050784_52002816.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6626b886207780d3171898512c0e485c3d2fa628d547ce8423275d3e93a3467
+size 20723091

checkpoint_p1/milestones/checkpoint_000059264_60686336.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5040ac5e837c40da5ca4059295b7a25a626f86652a0ece8e2ee996acc7a71dd5
+size 20723091

checkpoint_p1/milestones/checkpoint_000067776_69402624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f99288f31fa7cacf788d844ce23e567c7932b3b58f1de33acd60ac233fc384
+size 20723091

checkpoint_p1/milestones/checkpoint_000076256_78086144.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de4b78da9c2c73862279e21508b8eba723c29671d4def721276901a9611d9e0
+size 20723091

checkpoint_p1/milestones/checkpoint_000084800_86835200.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2181f0d525a4be9c829532a85d1280d416c9d3250baef69458a5d8c4c7152a93
+size 20723091

checkpoint_p1/milestones/checkpoint_000093312_95551488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36dd3c9ce5c2a60a319b4094bce79cd403cf140883c69e134a65605d93de8735
+size 20723091

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_demonattack",
-  "experiment": "atari_demonattack",
+  "experiment": "atari_demonattack_APPO",
   "train_dir": "./train_atari",
-  "restart_behavior": "resume",
+  "restart_behavior": "restart",
   "device": "gpu",
-  "seed": null,
+  "seed": 1234,
   "num_policies": 2,
-  "async_rl": false,
+  "async_rl": true,
   "serial_mode": false,
-  "batched_sampling": false,
+  "batched_sampling": true,
   "num_batches_to_accumulate": 2,
   "worker_num_splits": 1,
   "policy_workers_per_policy": 1,
   "max_policy_lag": 1000,
-  "num_workers": 8,
-  "num_envs_per_worker": 1,
-  "batch_size": 256,
-  "num_batches_per_epoch": 4,
+  "num_workers": 16,
+  "num_envs_per_worker": 2,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
   "num_epochs": 4,
   "rollout": 128,
   "recurrence": 1,
@@ -28,7 +28,7 @@
   "reward_clip": 1000.0,
   "value_bootstrap": false,
   "normalize_returns": true,
-  "exploration_loss_coeff": 0.01,
+  "exploration_loss_coeff": 0.0004677351413,
   "value_loss_coeff": 0.5,
   "kl_loss_coeff": 0.0,
   "exploration_loss": "entropy",
@@ -42,8 +42,8 @@
   "adam_eps": 1e-05,
   "adam_beta1": 0.9,
   "adam_beta2": 0.999,
-  "max_grad_norm": 0.5,
-  "learning_rate": 0.00025,
+  "max_grad_norm": 0.0,
+  "learning_rate": 0.0003033891184,
   "lr_schedule": "linear_decay",
   "lr_schedule_kl_threshold": 0.008,
   "lr_adaptive_min": 1e-06,
@@ -51,7 +51,9 @@
   "obs_subtract_mean": 0.0,
   "obs_scale": 255.0,
   "normalize_input": true,
-  "normalize_input_keys": null,
+  "normalize_input_keys": [
+    "obs"
+  ],
   "decorrelate_experience_max_seconds": 0,
   "decorrelate_envs_on_one_worker": true,
   "actor_worker_gpus": [],
@@ -63,14 +65,14 @@
   "flush_summaries_interval": 30,
   "stats_avg": 100,
   "summaries_use_frameskip": true,
-  "heartbeat_interval": 20,
-  "heartbeat_reporting_interval": 180,
-  "train_for_env_steps": 10000000,
+  "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": -1,
+  "save_milestones_sec": 1200,
   "save_best_every_sec": 5,
   "save_best_metric": "reward",
   "save_best_after": 100000,
@@ -104,7 +106,7 @@
   "use_record_episode_statistics": true,
   "with_wandb": true,
   "wandb_user": "matt-stammers",
-  "wandb_project": "atari",
+  "wandb_project": "atari_APPO",
   "wandb_group": "atari_demonattack",
   "wandb_job_type": "SF",
   "wandb_tags": [
@@ -122,16 +124,32 @@
   "pbt_target_objective": "true_objective",
   "pbt_perturb_min": 1.1,
   "pbt_perturb_max": 1.5,
-  "command_line": "--algo=APPO --env=atari_demonattack --experiment=atari_demonattack --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_demonattack --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_demonattack --experiment=atari_demonattack_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_demonattack --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_demonattack",
-    "experiment": "atari_demonattack",
+    "experiment": "atari_demonattack_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",
+    "wandb_project": "atari_APPO",
     "wandb_group": "atari_demonattack",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_demonattack_20230926_024740_154529"
+  "wandb_unique_id": "atari_demonattack_APPO_20231010_163350_973186"
 }

git.diff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f3fe545f35e5db1e419bf1e198c0bc5ef89459d55f59e2d06d3c108907e732
-size 14403396
+oid sha256:3357904f421d3f4924836316b1741bf64d5dd0e807d5e80ac07059b4c52a7008
+size 14426734

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a67fffbeed24d8156f7a3aa5e50f50645000316ee4a17dc0e0fa1b2d183cacfc
-size 6760195
+oid sha256:cc8c8cdd52dfe53b23835ac2c76ba6b775da94b34b4922b247191f8662f6e49c
+size 62152513