Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1696924052.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71d9064edb4c88a3b3ecafbfaf88570b9e71eb89d653341cd436e8e4b86abe7
+size 7531212

.summary/1/events.out.tfevents.1696924052.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8419fc9c48e6f6a340c7db13cbe17e4775650b03780990c132ca07711bfd1ae
+size 4354307

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_crazyclimber
     metrics:
     - type: mean_reward
-      value: 80730.00 +/- 21044.10
+      value: 146490.00 +/- 31801.05
       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_crazyclimber
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_crazyclimber
 ```
 
     
+## 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_crazyclimber --train_dir=./train_dir --experiment=appo-atari_crazyclimber
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_crazyclimber --train_dir=./train_dir --experiment=APPO-atari_crazyclimber
 ```
 
 
@@ -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_crazyclimber --train_dir=./train_dir --experiment=appo-atari_crazyclimber --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_crazyclimber --train_dir=./train_dir --experiment=APPO-atari_crazyclimber --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_000061280_62750720_reward_159.750.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f274a390d1cc8f1ad3040b3164fc85273ed96e014b13f40ea62ea417feaa305
+size 20740275

checkpoint_p0/checkpoint_000096992_99319808.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17184abec130156a6f0b625a6713665f6c695a06cd1e3399f7eb301542b057cb
+size 20740611

checkpoint_p0/checkpoint_000097696_100040704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8162d71cd6ba315ff8b822c5e2c373e0a6b9a9349de0209102db093f7d0982
+size 20740611

checkpoint_p0/milestones/checkpoint_000008384_8585216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09326879a6b81201dd3acfc4937acc5d63c5b504209d8cbbf7a226b372fbc747
+size 20741467

checkpoint_p0/milestones/checkpoint_000016928_17334272.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52abdef3ffdc28d638175c1fecc7f8a436555ff877ef88026b230309e8321f49
+size 20741523

checkpoint_p0/milestones/checkpoint_000025440_26050560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e552a9cb75d7f84b4f2ff132344302f3cbad644e9a24c40a6c52f81fead68e
+size 20741523

checkpoint_p0/milestones/checkpoint_000033952_34766848.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6c1daa9ca9beec142187847cab8fda4dcfdfc49140d8bd849465e85674f25f
+size 20741523

checkpoint_p0/milestones/checkpoint_000042496_43515904.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52399b7d953707e3cdb8e2336f871726e96ca49115a3d13840ed43a0ad09faa0
+size 20741523

checkpoint_p0/milestones/checkpoint_000051008_52232192.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f9ecd413aff60c6d34ba29b6b160fbc137e6a52ca40be7de50b15d4d157e6a
+size 20741523

checkpoint_p0/milestones/checkpoint_000059520_60948480.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6f0a07f99b1fe6d452f0b2f34b50a5804d177be0aeca543fb296d1476f2ed1
+size 20741523

checkpoint_p0/milestones/checkpoint_000068032_69664768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b778ddfc417317385296acf273101e52e18948c07a537a970810d46d9f8d93
+size 20741523

checkpoint_p0/milestones/checkpoint_000076544_78381056.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b95f01adf0d4a31816293b373ecc51531be6f29caba10de825ee6fc8e4e8ed6
+size 20741523

checkpoint_p0/milestones/checkpoint_000085056_87097344.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46facf7c7519f6bfe979567bc7d32ff49fa2f5460bdedfc3b7048129f657ac53
+size 20741523

checkpoint_p0/milestones/checkpoint_000093568_95813632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eee25ec42afaae7e223437eab86365eec38ae0ff9d0334aee30a595d56c475a
+size 20741523

checkpoint_p1/best_000093408_95649792_reward_160.730.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c90bae8acc9f5aed5252d9f6ebfa1623e7588668007a741edd99cf03c2ac0b
+size 20740275

checkpoint_p1/checkpoint_000098048_100401152.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3024385642b74242240826998d49f6cc3b5b5f74e82670f65b0a8b107df1219d
+size 20740611

checkpoint_p1/checkpoint_000098752_101122048.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4b39097b4b1a50db98d9eb17b2f17367e9032c1ef084a0ae4f406c0227d110
+size 20740611

checkpoint_p1/milestones/checkpoint_000008480_8683520.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3724c04824e41795061555917c42837a0bac96a9c5afbfab755724e2868beb
+size 20741467

checkpoint_p1/milestones/checkpoint_000017088_17498112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0aa1cc1307e6a8ef964ed7853f8b20c569c56e46f4a33ec34cc45b7f976ee1
+size 20741523

checkpoint_p1/milestones/checkpoint_000025696_26312704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6883f694876be122b80e12458790724fbe42c76593e20702268245f1520debb
+size 20741523

checkpoint_p1/milestones/checkpoint_000034304_35127296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443ecf50c23f3b10cfb715fbd184076564cf62995d6616964a14dda09d2650d8
+size 20741523

checkpoint_p1/milestones/checkpoint_000042912_43941888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d5fe9e041d3a0e957c498979af70c90660aa7e77791834335c10e583038b4c
+size 20741523

checkpoint_p1/milestones/checkpoint_000051552_52789248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029f8e996f3a1f1ad646523ac9170788bdfc6beef15b837919f0b1cfb03e7502
+size 20741523

checkpoint_p1/milestones/checkpoint_000060160_61603840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b354436fea2aaf593746c4f0f610f7696a838e7d899f9efb3a802f248d8953f8
+size 20741523

checkpoint_p1/milestones/checkpoint_000068768_70418432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8722ce47cdb77cd5505d0d18cd688b5a738aa140dfd3613b3a1500a0f2c8a17b
+size 20741523

checkpoint_p1/milestones/checkpoint_000077376_79233024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238e7427be079d93e55929d0f926c2fb433466621de49d7b652c94315368fcc9
+size 20741523

checkpoint_p1/milestones/checkpoint_000085984_88047616.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7bbe8085821bd26d5254df65b70980a33eb1daff4d251fc99717ffa47c90b9
+size 20741523

checkpoint_p1/milestones/checkpoint_000094592_96862208.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d19b7f5e55cbdfa8e87b095e9a2cb386741813b55ef16e0d6ce525c56829e59
+size 20741523

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_crazyclimber",
-  "experiment": "atari_crazyclimber",
+  "experiment": "atari_crazyclimber_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_crazyclimber",
   "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_crazyclimber --experiment=atari_crazyclimber --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_crazyclimber --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_crazyclimber --experiment=atari_crazyclimber_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_crazyclimber --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_crazyclimber",
-    "experiment": "atari_crazyclimber",
+    "experiment": "atari_crazyclimber_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_crazyclimber",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_crazyclimber_20230926_005437_311119"
+  "wandb_unique_id": "atari_crazyclimber_APPO_20231010_084729_743335"
 }

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 sha256:1e4b6604f1432e7208969ddc9cf06bdb947ca41826b7e10668410ae797df757c
-size 8890571
+oid sha256:7ca617ad6fbb53b782ee8c1ad498657d237666e8870d83cf45649e831d00d447
+size 12237912