Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697526735.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e841b0d473fb81ff1057890e0a308844176d943d006c07361ac0639a95a8065a
+size 7980230

.summary/1/events.out.tfevents.1697526735.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0980679e073e833dd73288bae74d8577f3143c10f4d6610c2c46072a207d3a
+size 4617090

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_zaxxon
     metrics:
     - type: mean_reward
-      value: 200.00 +/- 600.00
+      value: 23000.00 +/- 4562.24
       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_zaxxon
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_zaxxon
 ```
 
     
+## 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_zaxxon --train_dir=./train_dir --experiment=appo-atari_zaxxon
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_zaxxon --train_dir=./train_dir --experiment=APPO-atari_zaxxon
 ```
 
 
@@ -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_zaxxon --train_dir=./train_dir --experiment=appo-atari_zaxxon --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_zaxxon --train_dir=./train_dir --experiment=APPO-atari_zaxxon --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_000093824_96075776_reward_13.180.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac833f661948e5c4e8f0aa51110e46d6909ddc235ede481f6ffdbadc0e94c2c9
+size 20795763

checkpoint_p0/checkpoint_000097152_99483648.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2499f0ddb042ed90ed307917bad4eba927287da28cabafd2db489bd5ee1a4f7
+size 20796099

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5969a567719488b28a64b8577829589884b059b1dbd228649b27245317aaa5e
+size 20796099

checkpoint_p0/milestones/checkpoint_000007872_8060928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24e92959157595f0a96dbda0fd696259863c7af40a6821260de522f5cae59e1
+size 20796955

checkpoint_p0/milestones/checkpoint_000015872_16252928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:779ca19c25b251a80c8d182a70969ac2309effca13893b02e023adf96f4295b2
+size 20797011

checkpoint_p0/milestones/checkpoint_000023904_24477696.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ba03cb0d5d241d6df610e1efe40b8decf42d3fb02cc76f9fdbf569e92a0681
+size 20797011

checkpoint_p0/milestones/checkpoint_000031968_32735232.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1794d15ee0e21d84c6a45619502b809afc7208dcdb7c7cb1002a2770b1a3c7
+size 20797011

checkpoint_p0/milestones/checkpoint_000040032_40992768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617e9d5e124ddc2edd7df12a2b069a88a2a93180125837d13a34b82dfb0192c3
+size 20797011

checkpoint_p0/milestones/checkpoint_000048064_49217536.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764180cd389fa8181eef69001d091504238f1b3eaf4de87134862333f2d4cb28
+size 20797011

checkpoint_p0/milestones/checkpoint_000056096_57442304.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1037f8d2739d128c972f6474d7c533a50b63d1d760788c21b660bc12401e1ee2
+size 20797011

checkpoint_p0/milestones/checkpoint_000064160_65699840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02caa8f052757560813121e43eb406eec3bbb9d5b77a7bfa9de8312fa0b05ab
+size 20797011

checkpoint_p0/milestones/checkpoint_000072192_73924608.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf809932e2088ddcb878661847ac9ea9bc8ebf0184a78a940a55fa19a72fea3
+size 20797011

checkpoint_p0/milestones/checkpoint_000080224_82149376.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421a407d88c3a135091f485c734c6527873ab430173c88175ccb055e2766d3c6
+size 20797011

checkpoint_p0/milestones/checkpoint_000088288_90406912.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d24ef5af595386bbb7a356d1efb5edbc6938a15dd2df8abf17d34dfa3195498
+size 20797011

checkpoint_p0/milestones/checkpoint_000096352_98664448.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a0c0a89df7f36844425a0432c429507d674e08f026733a8f083731ace25557
+size 20797011

checkpoint_p1/best_000096096_98402304_reward_13.480.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea543a9c6ffdc05b5899c13af2fa30cf92affe002ab4f77d4081b8815a432255
+size 20795763

checkpoint_p1/checkpoint_000098112_100466688.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c8898cde624d5d7aa7957d55b75dd5481343f9cdcd3a3c109a904e5019d245
+size 20796099

checkpoint_p1/checkpoint_000098656_101023744.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78b3614a649ba8bd4ff43f7fcf406aa8e37995a6f03b9d1777ab13a21a8b5bf
+size 20796099

checkpoint_p1/milestones/checkpoint_000007904_8093696.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00274ada3f4d102902aaaffae54a812a6217eb9efc68f516125b44206c458da6
+size 20796955

checkpoint_p1/milestones/checkpoint_000015968_16351232.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1fce11d06c4899bf4f6f936ca1cd6c38fce2511a8512a46343ca8c991c1a8e9
+size 20797011

checkpoint_p1/milestones/checkpoint_000024096_24674304.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53912affed7ba43a16c2a123e45795866e9b78ceafa408cac40c62827004f897
+size 20797011

checkpoint_p1/milestones/checkpoint_000032224_32997376.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b8a37c7da0c1905a50322d664c5cdca9516324231c333e7c1c1351fc5103037
+size 20797011

checkpoint_p1/milestones/checkpoint_000040352_41320448.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9933ef0e485c61225deec1b638742dde0da67a21d564a264bc320565d67cca
+size 20797011

checkpoint_p1/milestones/checkpoint_000048448_49610752.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19179e069f79029da6c72521cb3e7b855b83862a42cbb3d2b0278dd1a4a424c
+size 20797011

checkpoint_p1/milestones/checkpoint_000056576_57933824.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c3d2b3c2d3bb1f1910db35fdf8c8840ba56186d5963d985f958896ee1e401a
+size 20797011

checkpoint_p1/milestones/checkpoint_000064704_66256896.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb05b0f755b27a21db3af0af1a09475781a06309c599f8a8a0c5f70d4117d44
+size 20797011

checkpoint_p1/milestones/checkpoint_000072832_74579968.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f64aee02a2b53c1da9d304c9788147b246fa987acf81db0c671be51d60f86f5
+size 20797011

checkpoint_p1/milestones/checkpoint_000080992_82935808.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bca256081317c71899287e10cbb7595bfe462c0023f3b276e448810532f791
+size 20797011

checkpoint_p1/milestones/checkpoint_000089152_91291648.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c7f99f54ac8498435ee3f4eaded9cc8d1f3c56b212b25c6b65751274d60e5a
+size 20797011

checkpoint_p1/milestones/checkpoint_000097312_99647488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328d0e242a94b7c806bf71912b5a6bdb484fd9564a609a0d37c8487929c9fc96
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_zaxxon",
-  "experiment": "atari_zaxxon",
+  "experiment": "atari_zaxxon_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_zaxxon",
   "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_zaxxon --experiment=atari_zaxxon --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_zaxxon --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_zaxxon --experiment=atari_zaxxon_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_zaxxon --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_zaxxon",
-    "experiment": "atari_zaxxon",
+    "experiment": "atari_zaxxon_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_zaxxon",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_zaxxon_20230927_173536_301769"
+  "wandb_unique_id": "atari_zaxxon_APPO_20231017_081212_436603"
 }

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 sha256:3c81c4bc75d3a46d41b9d14b52a48711b2bfdf05daf4db6ba2468da52589e0a7
-size 2898078
+oid sha256:c7782459c0b9426fa73430b3f974573a7a83140ef66c290535871fa3399aa16b
+size 10904833