Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697361721.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a911b08ccc2f57a44b118338d8757dd777f4c4c20f0e7dd45e7ce354b95557
+size 8459607

.summary/1/events.out.tfevents.1697361721.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d69cd7c0ec0c7b449f10c48bc71cde45e0f57cddb85f1d4646586f431fad456
+size 4875805

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_solaris
     metrics:
     - type: mean_reward
-      value: 1550.00 +/- 656.73
+      value: 1402.00 +/- 785.90
       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_solaris
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_solaris
 ```
 
     
+## 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_solaris --train_dir=./train_dir --experiment=appo-atari_solaris
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_solaris --train_dir=./train_dir --experiment=APPO-atari_solaris
 ```
 
 
@@ -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_solaris --train_dir=./train_dir --experiment=appo-atari_solaris --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_solaris --train_dir=./train_dir --experiment=APPO-atari_solaris --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_000008992_9207808_reward_6.130.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db88e58320250f9c9400a0dc9ebe3f228af19496824572b934f86954438c4f1
+size 20795763

checkpoint_p0/checkpoint_000097952_100302848.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de1b18761a03328866b64343864de85e856c4ed1a44984999fe248fa80f1bbe
+size 20796099

checkpoint_p0/checkpoint_000098592_100958208.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cbb15bcf164f42437f902d50cdff921039744f8083e032db4d54fe23af6236
+size 20796099

checkpoint_p0/milestones/checkpoint_000007520_7700480.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6d694e011c15220424b9c2fe60564791f9a7f5c157a5396a0118cc6747218e
+size 20796955

checkpoint_p0/milestones/checkpoint_000015104_15466496.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23da27a071076a3accec01d2be13c850825796331706e5504b5b0b61806803b
+size 20797011

checkpoint_p0/milestones/checkpoint_000022720_23265280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5dcbfaafad89c04f0f735904439e60fa928e13f64df55dabffea528854271f
+size 20797011

checkpoint_p0/milestones/checkpoint_000030272_30998528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c0a640fb7643af3ea315c1bbb01a2ffb697c5a85bf1c5d3dc4d3589167da40
+size 20797011

checkpoint_p0/milestones/checkpoint_000037888_38797312.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6265466721cdeb98f03a2721d601fd5fa9dd3f84e6bb6b26f8519dc7352bf6b5
+size 20797011

checkpoint_p0/milestones/checkpoint_000045440_46530560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5acf2cd7a23099d61b4ad938ac5e928c3a32ffc9a4f6b8f44c01f9578247b6f
+size 20797011

checkpoint_p0/milestones/checkpoint_000053056_54329344.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be802f5386d64b938dbc756cae185d7235c7205c713299982c8c3a762d4746c2
+size 20797011

checkpoint_p0/milestones/checkpoint_000060672_62128128.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b707be867409e0dc391fa8b219b5e9c0bfa9eec63c0a4a25536e4c30574e21
+size 20797011

checkpoint_p0/milestones/checkpoint_000068256_69894144.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc5887a6c5f38e4d52d03a7dead65998a61c1b44362a6e7a551341b38d67b7d
+size 20797011

checkpoint_p0/milestones/checkpoint_000075872_77692928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1944ca54ddd5a49aa937519224a77741fa709ed879ea6c9b957dc59a0d21328d
+size 20797011

checkpoint_p0/milestones/checkpoint_000083488_85491712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b842b2f2789d4f5794b29d46771756ee00944b8d1cd4e8fb0680268dd081c8a
+size 20797011

checkpoint_p0/milestones/checkpoint_000091104_93290496.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e1249e2539523918f472d401734e92d86163ff5dd416abb0d9add5633b38c4
+size 20797011

checkpoint_p1/best_000072480_74219520_reward_5.890.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c133b7175c3e996edfc9cb709dcb74e2b3a17e80af0b08fe4d72e676acf1a0
+size 20795763

checkpoint_p1/checkpoint_000097056_99385344.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea335b9b327ecd4d2e0c8cd75a3fed69ef1e349c631de65e70659656ec419c7a
+size 20796099

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ea53bb6f8d7d2253940b83aa7b2c631bd3ddfb000c9676feb8dbfa27f6ae8e
+size 20796099

checkpoint_p1/milestones/checkpoint_000007424_7602176.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b10f00f195c16b6c27f0d559b7d239037523e215c467afef79f2c0daa247ca
+size 20796955

checkpoint_p1/milestones/checkpoint_000014944_15302656.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da71143f2bfa98cc3f92e37c5f2c2be307a4699b3909956aec84c3e8420e1402
+size 20797011

checkpoint_p1/milestones/checkpoint_000022496_23035904.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf5ab678339d3a5a75f02d0b94cc7e8ae72fac48639b79bfd3958abc008cb56d
+size 20797011

checkpoint_p1/milestones/checkpoint_000030016_30736384.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90eb41e15a1c3f454f480fbda3090c05245a149e7f1c179c278568a68a417053
+size 20797011

checkpoint_p1/milestones/checkpoint_000037568_38469632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a10d2be5f11d4aae505543273638a48a48774cd7e6338ac13a9edeed08e6a2
+size 20797011

checkpoint_p1/milestones/checkpoint_000045088_46170112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fff8efaf7beada5d56dbd107bee31e450ff1a7df0be480034f5db99b5f7df1d
+size 20797011

checkpoint_p1/milestones/checkpoint_000052608_53870592.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc1c275583a4595b4d2da3a8d792edace3552e288ec0edad41aea6f200407c54
+size 20797011

checkpoint_p1/milestones/checkpoint_000060128_61571072.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b64dd6837f77e69b3108d7e64b814b94680804af81155d41b6c5fd2a3c22737
+size 20797011

checkpoint_p1/milestones/checkpoint_000067680_69304320.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36414bc63045109c331beda41f7c643142ca203f47c54f80745b9975be867c65
+size 20797011

checkpoint_p1/milestones/checkpoint_000075200_77004800.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20253df52e23fe0ab35696c9b7b7602dd7fec3375326051c423d362e6e9e8db3
+size 20797011

checkpoint_p1/milestones/checkpoint_000082720_84705280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e14c3e842b6aaa5523f5da1303f9cdc6634fbf32fc15156c17e51a0d188dea
+size 20797011

checkpoint_p1/milestones/checkpoint_000090272_92438528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f5ddae12c79bd6df1b3836a56525c166ee4f939b52f3c7bd6088231799ddda
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_solaris",
-  "experiment": "atari_solaris",
+  "experiment": "atari_solaris_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_solaris",
   "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_solaris --experiment=atari_solaris --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_solaris --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_solaris --experiment=atari_solaris_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_solaris --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_solaris",
-    "experiment": "atari_solaris",
+    "experiment": "atari_solaris_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_solaris",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_solaris_20230927_042503_529609"
+  "wandb_unique_id": "atari_solaris_APPO_20231015_102159_107962"
 }

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 sha256:81ab3cb078a19d9cae1a9b9c9134f3fa43d25e1c86c933d88f04cb6a58aa72db
-size 26688462
+oid sha256:638df15af9126b73ece804d2bfeaea3da5f14a72a0cdd92f1588f18922b6456c
+size 31088419