Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1695825953.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbf433adcb9fb7ae3c90fe79532e81099e74d053644544667b4782532be56fe
+size 2105091

.summary/1/events.out.tfevents.1695825953.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c028a7dda2db82ebf397b7526e28190b3c1f4aa79ee792032e3760f225026ca3
+size 1371808

README.md

@@ -0,0 +1,56 @@
+---
+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_wizardofwor
+      type: atari_wizardofwor
+    metrics:
+    - type: mean_reward
+      value: 2590.00 +/- 1905.49
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **atari_wizardofwor** 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_wizardofwor
+```
+
+    
+## 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_wizardofwor --train_dir=./train_dir --experiment=appo-atari_wizardofwor
+```
+
+
+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_wizardofwor --train_dir=./train_dir --experiment=appo-atari_wizardofwor --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_000034672_8876032_reward_4.870.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a5b131cd9eab21b0864db43173bb7ee75e8e058ba1598bceb0ab569a1614e3
+size 20746419

checkpoint_p0/checkpoint_000038464_9846784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186c8c69a8409ee3efe982d76a0be723adf7897a2718df0999120ed06f1c43bf
+size 20746755

checkpoint_p0/checkpoint_000039088_10006528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2e391938e5cbcb4dcfdf9e49bc9dc72adf181ddce9db9a0c45e1dbe9777df9
+size 20746755

checkpoint_p1/best_000038288_9801728_reward_5.250.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efff8c295213c21ad1946df87ab51860d9a19ee61acc68a3ebd1819859eacb26
+size 20746419

checkpoint_p1/checkpoint_000038464_9846784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f39842eb7ee0ef4a2adf0885afddf6653717a7bc04a1e7473766bcbb60f0be9
+size 20746755

checkpoint_p1/checkpoint_000039088_10006528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f60b5176e830e51293cabe8aacb0faf56e5065e511503c53e77c8e4065f5bf
+size 20746755

config.json

@@ -0,0 +1,144 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "atari_wizardofwor",
+  "experiment": "atari_wizardofwor",
+  "train_dir": "./train_atari",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": null,
+  "num_policies": 2,
+  "async_rl": false,
+  "serial_mode": false,
+  "batched_sampling": false,
+  "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_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": 0.01,
+  "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": 0.5,
+  "learning_rate": 0.00025,
+  "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": null,
+  "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": 20,
+  "heartbeat_reporting_interval": 180,
+  "train_for_env_steps": 10000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 120,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": -1,
+  "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",
+  "wandb_group": "atari_wizardofwor",
+  "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_wizardofwor --experiment=atari_wizardofwor --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_wizardofwor --wandb_job_type=SF --wandb_tags=atari",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "atari_wizardofwor",
+    "experiment": "atari_wizardofwor",
+    "train_dir": "./train_atari",
+    "num_policies": 2,
+    "with_wandb": true,
+    "wandb_user": "matt-stammers",
+    "wandb_project": "atari",
+    "wandb_group": "atari_wizardofwor",
+    "wandb_job_type": "SF",
+    "wandb_tags": [
+      "atari"
+    ]
+  },
+  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
+  "git_repo_name": "not a git repository",
+  "wandb_unique_id": "atari_wizardofwor_20230927_154551_007232"
+}

git.diff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f3fe545f35e5db1e419bf1e198c0bc5ef89459d55f59e2d06d3c108907e732
+size 14403396

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e0030ab1c5a4a651eb95644f0b49c3b47e2c9b3a8ab9631d8519ca5e66e073
+size 2271554