Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+sf_log.txt filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1714361447.41662289211e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2704d990433614c7663c1721d2aea91cd7322014b4cc93dcbea99f7d84614f4d
+size 106763012

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.v0.1.1
+```
+
+    
+## 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.v0.1.1
+```
+
+
+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.v0.1.1 --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:f70ac6b92420b99fc470b6ae3f6f269a0355f4f0fb4a217a3fb81383423eb193
+size 11696364

a20_40x40.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169a49f50570f1429884251272b83eb33d3d7eb4764db1a7576858cc8c1904af
+size 6315632

a5_25x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b3815cabba23999871e455de7c0cda46893d8628764e64a1ce98484b137263
+size 2020125

checkpoint_p0/best_000402516_6594822144_reward_0.764.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23f4e7b67ccddc6879aed47a4d62d8ec05a3c072bbe2e0289d7b80239c5e0fa
+size 38887866

checkpoint_p0/checkpoint_000458168_7506624512.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e0c7c5feb861721f044f91e794d8bcfa99fe253b3155ab83cf8b38bdd47b7c
+size 38889406

checkpoint_p0/checkpoint_000458577_7513325568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c8f02dc495b07baed962f73df68d060c28d7cf68324b76d1da6edd066bcabdf
+size 38889406

config.json

@@ -0,0 +1,159 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "GDY-PowerGrid",
+  "experiment": "p2.fa.s1",
+  "train_dir": "/workspace/metta/train_dir",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": 1,
+  "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": "metta",
+  "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=metta --experiment=p2.fa.s1 --seed=1 --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.s1",
+    "seed": 1,
+    "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": "metta",
+    "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": "1e6f44b10f61fc1cdcf59ec38035cda6e4d29622",
+  "git_repo_name": "https://github.com/daveey/metta.git",
+  "wandb_unique_id": "p2.fa.s1_20240428_203044_632178"
+}

sf_log.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a61cf9fb8bdb53026edb560c0b6c2a49fc54fc7acc0ffd02ae0e69b989970a13
+size 13197292