Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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
+a100_100x100.mp4 filter=lfs diff=lfs merge=lfs -text
+a20_40x40.mp4 filter=lfs diff=lfs merge=lfs -text
+a5_25x25.mp4 filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text
+sf_log.txt filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1714107045.41662289211e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e043181d4116da53f2a6145fefc0a059a31a60ea51868ae20850def6156c4f75
+size 1379884

.summary/0/events.out.tfevents.1714108128.41662289211e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d16566ba745b2ea09709a968c37b3151aca1e7c1d4544ec1bfad65ca36d8f55
+size 32275252

.summary/0/events.out.tfevents.1714147482.41662289211e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f93e2508bcd76f47d85e9f23bb6349b8760e5245fbd2baa7ed41449b42497aa
+size 50280497

.summary/0/events.out.tfevents.1714233454.41662289211e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5face2c99a5f9d204027e90cee32335430379f4cd954a36dcf6533b01592adfb
+size 23066420

.summary/0/events.out.tfevents.1714263469.41662289211e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ca441ab5cface2e48d112656524e06198f5f5ae2cfc18de1093c5ca0ee6c77
+size 32162827

.summary/0/events.out.tfevents.1714324047.41662289211e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df89d79d9955218fe2b9820e16b874bd44043dfc583254c02e6b379699dbbf8c
+size 27739576

README.md

@@ -0,0 +1,42 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+---
+
+A(n) **APPO** model trained on the **GDY-PowerGrid** 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 metta-ai/baseline.v0.1.0
+```
+
+    
+## Using the model
+
+To run the model after download, use the `enjoy` script corresponding to this environment:
+```
+python -m <path.to.enjoy.module> --algo=APPO --env=GDY-PowerGrid --train_dir=./train_dir --experiment=baseline.v0.1.0
+```
+
+
+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 <path.to.train.module> --algo=APPO --env=GDY-PowerGrid --train_dir=./train_dir --experiment=baseline.v0.1.0 --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.
+    

a100_100x100.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a204928f60ede7261cc9ebb74648909ce81fe427bd4f876d02708eff7b96a72e
+size 11911169

a20_40x40.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43620138c4785cf548bbae1bc24ef7fc70784fd2e6afc58fbf3ca43532fff8
+size 7300374

a5_25x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f731d5cb36af88f5dff3bfaf9b0da2001153178ebab538a6105a9478ff9078
+size 2405413

checkpoint_p0/best_000422462_6921617408_reward_0.757.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf64cfca89ba3c5f025c2f8391c390606b52f19720b1569c344152d5240c4b47
+size 38894330

checkpoint_p0/checkpoint_000701974_11501142016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c1a5ab512ceaaa0b5f4a4262b2b98e10886b866afe83fa3bb6975e611c4c48
+size 38889662

checkpoint_p0/checkpoint_000702383_11507843072.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87bb703e5ba9c22324922515148c480729eef7a8c715484a4eaec05f6d94fefe
+size 38889662

config.json

@@ -0,0 +1,158 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "GDY-PowerGrid",
+  "experiment": "p2.fa.clean",
+  "train_dir": "/workspace/metta/train_dir",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": null,
+  "num_policies": 1,
+  "async_rl": true,
+  "serial_mode": false,
+  "batched_sampling": false,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 2,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 50,
+  "num_workers": 32,
+  "num_envs_per_worker": 2,
+  "batch_size": 16384,
+  "num_batches_per_epoch": 1,
+  "num_epochs": 1,
+  "rollout": 256,
+  "recurrence": 256,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1.0,
+  "reward_clip": 1000.0,
+  "value_bootstrap": false,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.002,
+  "value_loss_coeff": 0.976,
+  "kl_loss_coeff": 0.0,
+  "aux_loss_coeff": 0.0,
+  "exploration_loss": "symmetric_kl",
+  "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-06,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 4.0,
+  "learning_rate": 0.0001,
+  "lr_schedule": "constant",
+  "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
+  "obs_subtract_mean": 0.0,
+  "obs_scale": 1.0,
+  "normalize_input": false,
+  "normalize_input_keys": null,
+  "decorrelate_experience_max_seconds": 150,
+  "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": 10,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": true,
+  "heartbeat_interval": 20,
+  "heartbeat_reporting_interval": 180,
+  "train_for_env_steps": 9999999999999,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 120,
+  "keep_checkpoints": 2,
+  "load_checkpoint_path": null,
+  "init_checkpoint_path": null,
+  "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_simple",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": true,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "elu",
+  "policy_initialization": "orthogonal",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": true,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": false,
+  "env_gpu_actions": false,
+  "env_gpu_observations": true,
+  "env_frameskip": 1,
+  "env_framestack": 1,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": false,
+  "episode_counter": false,
+  "with_wandb": true,
+  "wandb_user": "platypus",
+  "wandb_project": "sample_factory",
+  "wandb_group": null,
+  "wandb_job_type": "SF",
+  "wandb_tags": [],
+  "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,
+  "env_cfg": "{\"wall_density\": 0.01, \"altar:cost\": 100, \"cost:shield\": 0, \"num_agents\": 20, \"width\": 40, \"height\": 40, \"num_altars\": 5, \"num_chargers\": 10, \"num_generators\": 50}",
+  "command_line": "--aux_loss_coef=0 --recurrence=256 --rollout=256 --value_loss_coeff=0.976 --exploration_loss=symmetric_kl --exploration_loss_coeff=0.002 --policy_initialization=orthogonal --learning_rate=0.0001 --max_policy_lag=50 --nonlinearity=elu --load_checkpoint_kind=latest --normalize_input=False --batch_size=16384 --decorrelate_experience_max_seconds=150 --train_for_env_steps=9999999999999 --with_wandb=True --wandb_user=platypus --wandb_project=sample_factory --experiment=p2.fa.clean --rnn_num_layers=1 --rnn_size=512 --rnn_type=gru --env=GDY-PowerGrid --env_cfg={\"wall_density\": 0.01, \"altar:cost\": 100, \"cost:shield\": 0, \"num_agents\": 20, \"width\": 40, \"height\": 40, \"num_altars\": 5, \"num_chargers\": 10, \"num_generators\": 50}",
+  "cli_args": {
+    "env": "GDY-PowerGrid",
+    "experiment": "p2.fa.clean",
+    "max_policy_lag": 50,
+    "batch_size": 16384,
+    "rollout": 256,
+    "recurrence": 256,
+    "exploration_loss_coeff": 0.002,
+    "value_loss_coeff": 0.976,
+    "aux_loss_coeff": 0.0,
+    "exploration_loss": "symmetric_kl",
+    "learning_rate": 0.0001,
+    "normalize_input": false,
+    "decorrelate_experience_max_seconds": 150,
+    "train_for_env_steps": 9999999999999,
+    "load_checkpoint_kind": "latest",
+    "rnn_size": 512,
+    "rnn_type": "gru",
+    "rnn_num_layers": 1,
+    "nonlinearity": "elu",
+    "policy_initialization": "orthogonal",
+    "with_wandb": true,
+    "wandb_user": "platypus",
+    "wandb_project": "sample_factory",
+    "env_cfg": "{\"wall_density\": 0.01, \"altar:cost\": 100, \"cost:shield\": 0, \"num_agents\": 20, \"width\": 40, \"height\": 40, \"num_altars\": 5, \"num_chargers\": 10, \"num_generators\": 50}"
+  },
+  "git_hash": "c1f8312bb9edc5b2b815fa011904740d7104e699",
+  "git_repo_name": "https://github.com/daveey/metta.git",
+  "wandb_unique_id": "p2.fa.clean_20240425_215042_340478"
+}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43620138c4785cf548bbae1bc24ef7fc70784fd2e6afc58fbf3ca43532fff8
+size 7300374

sf_log.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed454c986aff1e099b7f7bb59383a80ec27187acb0fcb605e7997b9914d708bf
+size 20942792