Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697346952.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b9b3c7089f69eb2e0e88ec6850622469c0b6aa984669d9523995b4366f36d4a
+size 7970810

.summary/1/events.out.tfevents.1697346952.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550c6b96fbb18ea440469b055ce038d085575d9a88f202dd950fdd600af7c1db
+size 4611340

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_skiing
     metrics:
     - type: mean_reward
-      value: -28038.00 +/- 5517.54
+      value: -27467.60 +/- 3896.12
       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_skiing
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_skiing
 ```
 
     
+## 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_skiing --train_dir=./train_dir --experiment=appo-atari_skiing
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_skiing --train_dir=./train_dir --experiment=APPO-atari_skiing
 ```
 
 
@@ -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_skiing --train_dir=./train_dir --experiment=appo-atari_skiing --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_skiing --train_dir=./train_dir --experiment=APPO-atari_skiing --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_000049536_50724864_reward_-1122.640.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa73ab046ebee67f7fe6ecc5df2b91606b2907941c4b109252a81288f3a9c29e
+size 20703411

checkpoint_p0/checkpoint_000098432_100794368.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c91de21081ee5a98dc05f419525b1534f85748894369d98954eb2e883df3804
+size 20703747

checkpoint_p0/checkpoint_000098976_101351424.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a2801f5d122ce38789841167915855280b63c82c9a57574fa1e6ae6823319a
+size 20703747

checkpoint_p0/milestones/checkpoint_000008032_8224768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb8571012ae3e717c56d72ba9ed3107c7b45cdc52ddb527d239f5dd212b13df
+size 20704603

checkpoint_p0/milestones/checkpoint_000016192_16580608.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737fc8fb97cb938bb3e58f88bd101cb22eb4fbb75237c4be001cd078e5336821
+size 20704659

checkpoint_p0/milestones/checkpoint_000024352_24936448.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3fbe1de2b4f9990aac268fecb05ef36eabca06fc5fef3fb050c6db22575fcb
+size 20704659

checkpoint_p0/milestones/checkpoint_000032480_33259520.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efedcd7680adf259591ae56cee920bba94650a068133b991b7cca1b45c78ef6f
+size 20704659

checkpoint_p0/milestones/checkpoint_000040608_41582592.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9922cbffd220ab9a95c7038d871c5a3e6fbb8e099dc11d480b0eca779f1a736c
+size 20704659

checkpoint_p0/milestones/checkpoint_000048736_49905664.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c534ec157873d1ab4674a30ff5565d68393757d70ed5871bf6cf1cdfa1043bd
+size 20704659

checkpoint_p0/milestones/checkpoint_000056864_58228736.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a23f94cf9cf5f8f03cc9b1dd916f8dd85928395bd580c9d111d59d8a9e70d2
+size 20704659

checkpoint_p0/milestones/checkpoint_000065024_66584576.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05d1d898db3ed6c8b8701808d4cf7bbc9fac6aff95cf9ae9ffb7e1d169561ce
+size 20704659

checkpoint_p0/milestones/checkpoint_000073152_74907648.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39c536cece1147499cebfc5dedc3d40b5e79976545ea924dc93a3029483bfeb5
+size 20704659

checkpoint_p0/milestones/checkpoint_000081312_83263488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6985e058b9d217371e84b876751bcbe1a29277f4dcdf00221eed4f9805b2af0a
+size 20704659

checkpoint_p0/milestones/checkpoint_000089472_91619328.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1feab1cf5a752444c1605fba60bcb69d7115b9980dfe55f14dc01e6bd0528fe
+size 20704659

checkpoint_p0/milestones/checkpoint_000097600_99942400.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f23a37248e502e99624107489eea6c12406eb76f7a22bb62641eb08b5c11efe
+size 20704659

checkpoint_p1/best_000094432_96698368_reward_-711.520.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ffb12db1286a2337f57e9f5f9768bcf791e28e93d19cd29c06212b95d1df09
+size 20703411

checkpoint_p1/checkpoint_000097120_99450880.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3113c6be9c6593f0bee4514a3ddd6effb248200907d270713ad2628aadeae5ac
+size 20703747

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71df199894f56e7472dcc4f8291a3e7981c30f2eb8153d006e2be7f083cd526
+size 20703747

checkpoint_p1/milestones/checkpoint_000007936_8126464.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b594f73c013430a96c5e134807708c8777d8f7806c5a655a84eef69bc3b3a459
+size 20704603

checkpoint_p1/milestones/checkpoint_000015968_16351232.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3f1434b48acf9a5498d3de43d332ac7941e08ad53f8ccff2644943d9bfbd40
+size 20704659

checkpoint_p1/milestones/checkpoint_000024032_24608768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc4bae8a0f4a6d3cf0e924276051d64e485176bfb41cb3d05807a2b882d6219
+size 20704659

checkpoint_p1/milestones/checkpoint_000032064_32833536.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978db3ca3b7c894dc33b639d1230ecff8fb04ba13121549b6f0e85278f7ffd0c
+size 20704659

checkpoint_p1/milestones/checkpoint_000040096_41058304.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdcd486ef8bf77756f70ac88bcc55139080837e373eb0bdb0cf056d960b01bdb
+size 20704659

checkpoint_p1/milestones/checkpoint_000048128_49283072.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132ed4cac7cea9801c339aa6e933b842a97dff01379fce1d5e57859a6683fdd1
+size 20704659

checkpoint_p1/milestones/checkpoint_000056192_57540608.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6ba94fd3423f702cdda6ad5afd3772e56c4dfbf60e5c4944736a50007bb8e5
+size 20704659

checkpoint_p1/milestones/checkpoint_000064224_65765376.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb212ba4c3cf4241a178901f76ec306db3b0dd726ae563ad070b34e09402de2
+size 20704659

checkpoint_p1/milestones/checkpoint_000072256_73990144.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b1b5115867ac5389b7938da2e4ede95e853706967d5830efd4377e92602726
+size 20704659

checkpoint_p1/milestones/checkpoint_000080288_82214912.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47f0659f886df052cd02d557e3d0674e860cc31e7a8df69c37e8f36d70db251
+size 20704659

checkpoint_p1/milestones/checkpoint_000088320_90439680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0b9444aa69de027a057f1af99629dcd3abfcc921532ef4cb39567ab7ca1de7
+size 20704659

checkpoint_p1/milestones/checkpoint_000096320_98631680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d109d57ef0383210a8fb01dcd75652ce2526477bf88b046de944f70ff1e2eb3
+size 20704659

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_skiing",
-  "experiment": "atari_skiing",
+  "experiment": "atari_skiing_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_skiing",
   "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_skiing --experiment=atari_skiing --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_skiing --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_skiing --experiment=atari_skiing_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_skiing --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_skiing",
-    "experiment": "atari_skiing",
+    "experiment": "atari_skiing_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_skiing",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_skiing_20230927_032908_788649"
+  "wandb_unique_id": "atari_skiing_APPO_20231015_061550_065574"
 }

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:e591aba5eb6ac6af0ea06026328300f41a004f8e7aafd895e254267a28c738a2
-size 4677758
+oid sha256:67b27d86ec68b97ff58fea1161560a40196405ef28acd9fb3073e1d4f5d44200
+size 4349444