Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697136946.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6951bd451c6cfaa92acde4daac3f9a7260d7523751f66927547e2eed01a01a55
+size 8334693

.summary/1/events.out.tfevents.1697136946.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3f8e737ea329ff6fd6729c6d58ee3c512084f35f0a877692b5991f24c5da06
+size 4816682

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_krull
     metrics:
     - type: mean_reward
-      value: 6770.00 +/- 2730.58
+      value: 11250.00 +/- 1150.31
       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_krull
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_krull
 ```
 
     
+## 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_krull --train_dir=./train_dir --experiment=appo-atari_krull
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_krull --train_dir=./train_dir --experiment=APPO-atari_krull
 ```
 
 
@@ -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_krull --train_dir=./train_dir --experiment=appo-atari_krull --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_krull --train_dir=./train_dir --experiment=APPO-atari_krull --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_000093728_95977472_reward_297.260.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d42179ba7bcfcf46a6410fbe1f489b5e5c020187da6d61bc9b5275d7d7c5e8
+size 20795763

checkpoint_p0/checkpoint_000097504_99844096.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4173c4ae3510e39dc59971092e2909fff371708f30696f7c3139da3a50bc68d
+size 20796099

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a8a23c711aeadb3d9e4b10fa2fc4584d24af8b7c10dd7055e4cd680a428d60
+size 20796099

checkpoint_p0/milestones/checkpoint_000007584_7766016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11423c209c89ce3a430edef62475b718650570718886f9b82dd976692ce6151d
+size 20796955

checkpoint_p0/milestones/checkpoint_000015264_15630336.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6723c7cf208cfed58dd1decf10ad288140a3f1046c9987937cd678738cf536
+size 20797011

checkpoint_p0/milestones/checkpoint_000022944_23494656.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706a4e0ee909c9def3bf207dab0350be77a55c4c37caaeeb385cdd67ac62fb53
+size 20797011

checkpoint_p0/milestones/checkpoint_000030624_31358976.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336bc5dbc66f241f7d1c2d9225c849ed3f61eb5bea74e7255ab516e6916de215
+size 20797011

checkpoint_p0/milestones/checkpoint_000038336_39256064.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae20a7e1be9ea5790480fb6d7a445e93d0e25653d9d1e8d277e23d10d659ff7d
+size 20797011

checkpoint_p0/milestones/checkpoint_000046016_47120384.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9812208af6ce0b0477711b731647ef8511cab55e1de5918e7979142f1600d8a9
+size 20797011

checkpoint_p0/milestones/checkpoint_000053696_54984704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd67980251c1b0ff0d488bc60cfd44b933f6317f540f4d914fe0d745cac7450
+size 20797011

checkpoint_p0/milestones/checkpoint_000061408_62881792.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3ceaf2d52cf08ae7a2f483cf26cdabf63df797c8e942dc1eaf63091ec425f4
+size 20797011

checkpoint_p0/milestones/checkpoint_000069088_70746112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e9e54cd0f12c162f93966f5757fa046218328e1f81d9108b612954025b2863f
+size 20797011

checkpoint_p0/milestones/checkpoint_000076768_78610432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f6a53a948352c5dc1e53aacd36caa5bdc4bc08b23acb2b64ba3e671aaceb68
+size 20797011

checkpoint_p0/milestones/checkpoint_000084448_86474752.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:713f3c6d0981619491624f783a54ab63aec1b2600f46c6517882c12d5ac94e6e
+size 20797011

checkpoint_p0/milestones/checkpoint_000092128_94339072.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae6bdade46c7c1e2a1d79546693026d96a56da28a7f985f6d0085d74de5383d
+size 20797011

checkpoint_p1/best_000086624_88702976_reward_294.050.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7b1a7ac5fa60cff3aef3fc91313c6ba0c23c64a0881d078307a4c73f66d59c
+size 20795763

checkpoint_p1/checkpoint_000097952_100302848.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca424a54229b9986da6ac20ea390a3face4cd51d8d14b4c07a8f10ff6b147a68
+size 20796099

checkpoint_p1/checkpoint_000098144_100499456.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc48631dcae5274bc0ced2222c2f9bfb36e5c97abfd956d91644ee27c2093cd
+size 20796099

checkpoint_p1/milestones/checkpoint_000007616_7798784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ddb718805b6732bea0ae9243f8bc45e4cc7f483b881dc0f5bb53a256db29322
+size 20796955

checkpoint_p1/milestones/checkpoint_000015360_15728640.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1860567359d546697306e3e1c2f38d4969cbef5f2cb6dda1aebdd112928185
+size 20797011

checkpoint_p1/milestones/checkpoint_000023104_23658496.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da971d5b8fa467a5fe621652019fc02f07262bf4285163cad6e9954a72aad9a8
+size 20797011

checkpoint_p1/milestones/checkpoint_000030816_31555584.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff92f09c72715626d858b27db4211b1ee690cc812b7165772df5b27076e5dd95
+size 20797011

checkpoint_p1/milestones/checkpoint_000038528_39452672.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40b58cf18f1b75b0e938689b1b0ec760d380b82cbb69053189b6c3050e0f2cd
+size 20797011

checkpoint_p1/milestones/checkpoint_000046240_47349760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe8e9808664495647514231f48f1748be2616f26187801064400dc276d07509
+size 20797011

checkpoint_p1/milestones/checkpoint_000053984_55279616.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8163b0b3ed30e989e4361f4290962f6ab14ff4d0ca819a407f267c7a35d2e14
+size 20797011

checkpoint_p1/milestones/checkpoint_000061696_63176704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e0b6a135ab9ea434b68cd4c6444c93a0ed990cbee88b83310b2935298a0976f
+size 20797011

checkpoint_p1/milestones/checkpoint_000069440_71106560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b340a172a2212d9833ece4ee6ca515cff36b2a98d3afad7a6be0d50431e6fb
+size 20797011

checkpoint_p1/milestones/checkpoint_000077120_78970880.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2176d40263cbcc434ca541d9e058f3544b8f7dc6c84ebb08cd55ed39670e2c68
+size 20797011

checkpoint_p1/milestones/checkpoint_000084864_86900736.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d004ea7beee8fb6db388474ffa1be44fa54b18f900cbec3a2ccd5388c793e554
+size 20797011

checkpoint_p1/milestones/checkpoint_000092544_94765056.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4b029e1cb91ae48e92afc9ab4aa04ef31119baf57d4ac5634f7361d105e3f6
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_krull",
-  "experiment": "atari_krull",
+  "experiment": "atari_krull_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_krull",
   "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_krull --experiment=atari_krull --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_krull --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_krull --experiment=atari_krull_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_krull --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_krull",
-    "experiment": "atari_krull",
+    "experiment": "atari_krull_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_krull",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_krull_20230926_141810_541626"
+  "wandb_unique_id": "atari_krull_APPO_20231012_195543_777732"
 }

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 sha256:5b4ba2d7a474f3ba0a32e662a3e4bbc23e5b29672c9efe4071e3064baef54005
-size 6811451
+oid sha256:219207e463dd607733a5808799e5b68ca4f3d286374440d50697480a88b7f3a3
+size 9258300