Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+git.diff filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1696761976.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8f4e90d1dc7a1fb61bf2c8ed6c0218b3b3766397fb790c4ac2d43624c5c858
+size 7681863

.summary/1/events.out.tfevents.1696761976.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c552183378f2e13fbbca6b3b16176fca3e097dfd699b943cb19ca7e7b2c773
+size 4443936

README.md

@@ -0,0 +1,169 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+model-index:
+- name: APPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: atari_asteroid
+      type: atari_asteroid
+    metrics:
+    - type: mean_reward
+      value: 2228.00 +/- 433.72
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **atari_asteroid** environment.
+
+This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
+Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+
+
+## Downloading the model
+
+After installing Sample-Factory, download the model with:
+```
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_asteroid
+```
+
+    
+## 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_asteroid --train_dir=./train_dir --experiment=APPO-atari_asteroid
+```
+
+
+You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
+See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
+    
+## Training with this model
+
+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_asteroid --train_dir=./train_dir --experiment=APPO-atari_asteroid --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_000082304_84279296_reward_10.620.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac5324715ecb9fe9377c2ce332efe3a1104d60185e5921bd77620fdc8454e85
+size 20770995

checkpoint_p0/checkpoint_000096928_99254272.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f8cc370187ff610f55509995fd8acb7fc87305670933a8e04b85361c033361
+size 20771459

checkpoint_p0/checkpoint_000097696_100040704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fdd17a2841c2da087a24665586469cbad1812b901fefe1714f0ee29ac5345a
+size 20771459

checkpoint_p0/milestones/checkpoint_000008256_8454144.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3609699c419f9df342deed397b88f002c7e0a7ef5e1da521f67967eda6caaac9
+size 20772379

checkpoint_p0/milestones/checkpoint_000016608_17006592.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29efc9e1f9b8b812d30ddd352c47d9f92e366da7b531afc461932ac18d8da528
+size 20772435

checkpoint_p0/milestones/checkpoint_000024992_25591808.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81237526220ffd36326313e9900bef53235ed23ce0bad5387da897fbc2e96c91
+size 20772435

checkpoint_p0/milestones/checkpoint_000033344_34144256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15db792268c93699b72a789691c210185514034773863415bb257ee7330c742c
+size 20772435

checkpoint_p0/milestones/checkpoint_000041728_42729472.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187a9bcf9d04bce96552f47fc2d27444096066acbd7135d759e5e5672ed289db
+size 20772435

checkpoint_p0/milestones/checkpoint_000050080_51281920.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06cfb81c075f763328eb698e3017c2c7ba833492d5942e8125c57437ecc7576a
+size 20772435

checkpoint_p0/milestones/checkpoint_000058464_59867136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef32af551faa10f7c43f8baab276eec3335b6c69b50ef4778f51954ca89c8930
+size 20772435

checkpoint_p0/milestones/checkpoint_000066816_68419584.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:040e3e29ca67cec5ab1e7eb83208288460b889504a931ecaf88e81dca0b67700
+size 20772435

checkpoint_p0/milestones/checkpoint_000075168_76972032.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c800b373eb336519756a8eafdb8c3c0818528588007d4e37554f1a9f4c67494d
+size 20772435

checkpoint_p0/milestones/checkpoint_000083552_85557248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac7217173198abdd22b1a1145cbf4b1d4e00a6ea24f0faa75f0d262f7f0ccf2
+size 20772435

checkpoint_p0/milestones/checkpoint_000091936_94142464.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e39ab9a5409bb6a9e7ea6e87c5b12038d235de4d7ff14667fed27b387deda8
+size 20772435

checkpoint_p1/best_000097536_99876864_reward_37.830.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d88ff32c2492eabd52670f1dc3eaf7f3867e671e29f697bc986912dfe7a785
+size 20770995

checkpoint_p1/checkpoint_000097088_99418112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765478806f20f2a05531b3b5329fc17c9b3d595c17952ee5434602f415a8f1fa
+size 20771459

checkpoint_p1/checkpoint_000097856_100204544.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df14dc35011fb7ef4d75c84eebbe3957f7e2d926e574b67fbad8064647110a84
+size 20771459

checkpoint_p1/milestones/checkpoint_000008256_8454144.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c503381a537f79966613bf6f7d0cdec71d56aea510abd653e9de9d39dd2cb6ed
+size 20772379

checkpoint_p1/milestones/checkpoint_000016640_17039360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccaaa3bbedee13cfb6c47e221e4f035909720eff7bcc91418476320af7556223
+size 20772435

checkpoint_p1/milestones/checkpoint_000025024_25624576.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c421e5dda4681554f2a6f285ffb0c9aa8a3da2f61a35ab56dbdf65a687c97410
+size 20772435

checkpoint_p1/milestones/checkpoint_000033376_34177024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0515a5930b5fb44c0dd3ecc63446e2716d1b2a74609da76375c8dc9d74ea4bd4
+size 20772435

checkpoint_p1/milestones/checkpoint_000041760_42762240.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080f148deebfee6cab44d1ade88b750a27dba446079d6e8d3b9e7761992a325c
+size 20772435

checkpoint_p1/milestones/checkpoint_000050112_51314688.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42736658f6ea6481893f3fbc84075abc9f6620c9b77641435156a00c8908653e
+size 20772435

checkpoint_p1/milestones/checkpoint_000058496_59899904.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856fff3c44e8dbb5af2652b862d481d82f2b9711488a7c59072b9df2e781354b
+size 20772435

checkpoint_p1/milestones/checkpoint_000066880_68485120.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a309013a11e8206fa3714d0608d47069e9c493a9ff9d8f6a72b9d0e524222e
+size 20772435

checkpoint_p1/milestones/checkpoint_000075264_77070336.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1b671e35f52411c5e5c56e14b4b73e74c2bfdeda40cd4c2139078f4c847ad4
+size 20772435

checkpoint_p1/milestones/checkpoint_000083648_85655552.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e48c45142d83e76569ce8863563d7a4f135469e92197f9ddf15168fec1f36ee
+size 20772435

checkpoint_p1/milestones/checkpoint_000092032_94240768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0791e7ff97be93dc47d978441f8e69f85112a5ff4fbfd5545d02ef3037910730
+size 20772435

config.json

@@ -0,0 +1,162 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "atari_asteroid",
+  "experiment": "atari_asteroid_APPO",
+  "train_dir": "./train_atari",
+  "restart_behavior": "restart",
+  "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,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": true,
+  "with_wandb": true,
+  "wandb_user": "matt-stammers",
+  "wandb_project": "atari_APPO",
+  "wandb_group": "atari_asteroid",
+  "wandb_job_type": "SF",
+  "wandb_tags": [
+    "atari"
+  ],
+  "with_pbt": false,
+  "pbt_mix_policies_in_one_env": true,
+  "pbt_period_env_steps": 5000000,
+  "pbt_start_mutation": 20000000,
+  "pbt_replace_fraction": 0.3,
+  "pbt_mutation_rate": 0.15,
+  "pbt_replace_reward_gap": 0.1,
+  "pbt_replace_reward_gap_absolute": 1e-06,
+  "pbt_optimize_gamma": false,
+  "pbt_target_objective": "true_objective",
+  "pbt_perturb_min": 1.1,
+  "pbt_perturb_max": 1.5,
+  "command_line": "--algo=APPO --env=atari_asteroid --experiment=atari_asteroid_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_asteroid --wandb_job_type=SF --wandb_tags=atari",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "atari_asteroid",
+    "experiment": "atari_asteroid_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_APPO",
+    "wandb_group": "atari_asteroid",
+    "wandb_job_type": "SF",
+    "wandb_tags": [
+      "atari"
+    ]
+  },
+  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
+  "git_repo_name": "not a git repository",
+  "wandb_unique_id": "atari_asteroid_APPO_20231008_114614_125146"
+}

git.diff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3357904f421d3f4924836316b1741bf64d5dd0e807d5e80ac07059b4c52a7008
+size 14426734