Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,24 @@ 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
+a20_40x40.mp4 filter=lfs diff=lfs merge=lfs -text
+a20_b4_40x40.mp4 filter=lfs diff=lfs merge=lfs -text
+a20_r4_40x40.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_altar_100x10.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_altar_100x25.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_altar_10x10.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_altar_25x25.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_empty_free_100x10.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_empty_free_100x100.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_empty_free_100x25.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_empty_free_10x10.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_empty_free_25x25.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_empty_move_cost_25x25.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_resources_100x10.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_resources_100x25.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_resources_25x25.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_resources_competition_10x10_2a.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_resources_competition_25x25_2a.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_resources_competition_25x25_3a.mp4 filter=lfs diff=lfs merge=lfs -text
+behaviors_resources_move_cost_25x25.mp4 filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1719510552.174d47ed6df0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b470dc1afe8f6cc196026f3300d44298d04f833650a01cc6585218904eefc7
+size 2173362

.summary/0/events.out.tfevents.1719519566.174d47ed6df0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb3ed2ace35519e90edb902a555434602fb6f7ba5e03387af45962b96364f4f
+size 849492

.summary/0/events.out.tfevents.1719520908.174d47ed6df0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7154d56732c1b8befd97122149db767ed0d6cd475903bea1ea23562e0986032c
+size 67333019

.summary/0/events.out.tfevents.1719603497.174d47ed6df0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0871662e964d336286435d1e5091e1a3054e9f02a849bb35b551620173ee34d4
+size 17603572

.summary/0/events.out.tfevents.1719634086.174d47ed6df0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49949a5fcfb31bf877c1700a828b26922aa7474bdaeb505a9ed88b2a021149cb
+size 603878

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-MettaGrid** 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.v0.5.6
+```
+
+    
+## 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-MettaGrid --train_dir=./train_dir --experiment=baseline.v0.5.6
+```
+
+
+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-MettaGrid --train_dir=./train_dir --experiment=baseline.v0.5.6 --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.
+    

a20_40x40.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b771405c1f50ab756af5522f95e9b1385a533493be76ed9c7011156accf06d2c
+size 2184627

a20_b4_40x40.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97f6125569a626ffe9531cb2748055d596ced299271bfab91007474cb22a791
+size 1620370

a20_r4_40x40.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6377c4fda80ebe20963c402d76daddebdd08b43fd57c0759d9da7f6afdb1a87f
+size 2491685

behaviors_altar_100x10.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d49fca75271a07b52e73dc8f1bd113866a83668529ee1d38daa9689f494df9
+size 1494492

behaviors_altar_100x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18022a72b23a68c84cc5d5fb4c77319cafdd9721d8456fdbd5c68482a5937984
+size 2670674

behaviors_altar_10x10.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9faf240154142387e088f3bf2b155c23ec69319574534fdbb7536ed24d603ba6
+size 1225774

behaviors_altar_25x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1360ac06f7c2f13176c842bb6e8cc7c9b53af245de80bbc5c14998e0b47f0f
+size 2721086

behaviors_empty_free_100x10.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ddd1d024463dbaed3e9ff49806bf978f18846be659f6b29302e49a8d57bdf8
+size 1645663

behaviors_empty_free_100x100.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b464dd63a2bcefaa81619f72a7a4acc399ae72dc70e9b29dc4e3ba949d4dfb1a
+size 8103551

behaviors_empty_free_100x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ca72ec50ae8afd4318374d787ab1f034a534b55f3d9a4bde64a983c7dddff2
+size 2758164

behaviors_empty_free_10x10.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6635228cf09e86a850a2c4cf93c26242b1598f8c0fc1b032694eb3051981a3ed
+size 1443723

behaviors_empty_free_25x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b837f3e50eec31f6b1d9645e5b3b7087c8817d0bddb5d026b84d7e8f3d61af20
+size 3237727

behaviors_empty_move_cost_25x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac1f9076fc501f67c1acc07a509c9195df9593cc0864dbe721286265970c7b7
+size 3193789

behaviors_resources_100x10.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d4520ce709312c1f3a5b1d76944ab882901c36029bdcf283a9ae9e84976728
+size 1545935

behaviors_resources_100x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95069415bf9f4795b18276a5138a44e7005ab2ff9b95e7b5422be1bccc2c6e46
+size 2203448

behaviors_resources_25x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9615cae9fad23b64ec5e1cffe134d9a6ec7c35ee45c6bed4fa92734a59532859
+size 3017513

behaviors_resources_competition_10x10_2a.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd81a3d631741a03e2c95d805bdeeb43cae04df39cfff709bbceebcb614808e7
+size 1309580

behaviors_resources_competition_25x25_2a.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82495f4d871ce9d667f54b1fe95f5ab187e1ba6de36c7949824ca905f7fd94e8
+size 3864438

behaviors_resources_competition_25x25_3a.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6b09a1a47aa431e4c8f050973706db4fa57f3f58631c7e85d7dd1670e1acf2
+size 3945061

behaviors_resources_move_cost_25x25.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cdcfa5680c48395c7630c4a87f2424014e8a991e0d101c14d9095761842d5fe
+size 1871806

checkpoint_p0/best_000274487_4497195008_reward_0.873.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21010bb5070e904a5448b3bfc366ebdd9a10215c53dcc57350458f72a4d2b1a0
+size 39046714

checkpoint_p0/checkpoint_000285577_4678893568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea9e477784cdef4a06acc48e1f47ddd1440af36a268da74533be04e5511e29fe
+size 39048154

checkpoint_p0/checkpoint_000285885_4683939840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f62d02985d195b29ae1bfc225aedccb52d9cbd05dd4c600b06115cdbe94098
+size 39048154

config.json

@@ -0,0 +1,162 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "GDY-MettaGrid",
+  "experiment": "p2.sf",
+  "train_dir": "./train_dir/sample_factory",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": 0,
+  "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": "platypus",
+  "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": "{\"name\": \"GDY-MettaGrid\", \"_target_\": \"env.griddly.mettagrid.gym_env.MettaGridGymEnv\", \"max_action_value\": 10, \"hidden_features\": {\"grid_obs\": [\"agent:energy\", \"agent:hp\"]}, \"game\": {\"obs_width\": 11, \"obs_height\": 11, \"max_steps\": 5000, \"tile_size\": 16, \"num_agents\": 20, \"no_energy_steps\": 500, \"objects\": {\"agent\": {\"initial_energy\": 250, \"max_energy\": 250, \"max_inventory\": 5, \"freeze_duration\": 10, \"energy_reward\": false, \"hp\": 1, \"mortal\": false, \"upkeep\": {\"time\": 0, \"shield\": 1}, \"use_cost\": 0}, \"altar\": {\"hp\": 30, \"cooldown\": 2, \"use_cost\": 100}, \"converter\": {\"hp\": 30, \"cooldown\": 2, \"energy_output\": {\"r1\": 50, \"r2\": 10, \"r3\": 1}}, \"generator\": {\"hp\": 30, \"cooldown\": 5, \"initial_resources\": 30, \"use_cost\": 0}, \"wall\": {\"density\": 0.01, \"hp\": 10}}, \"actions\": {\"move\": {\"cost\": 0}, \"rotate\": {\"cost\": 0}, \"jump\": {\"cost\": 3}, \"shield\": {\"cost\": 0}, \"transfer\": {\"cost\": 10}, \"use\": {\"cost\": 0}, \"attack\": {\"cost\": 5, \"damage\": 5}}, \"map\": {\"layout\": {\"rooms_x\": 1, \"rooms_y\": 1, \"rooms\": [[\"base\", \"wild_1\", \"base\"], [\"wild_2\", \"center\", \"wild_2\"], [\"base\", \"wild_1\", \"base\"]]}, \"room\": {\"width\": 25, \"height\": 25, \"num_agents\": 5, \"objects\": {\"agent\": 5, \"altar\": 1, \"converter\": 3, \"generator\": 15, \"wall\": 10}}, \"wild_1\": {\"width\": 10, \"height\": 15, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 1, \"converter\": 1, \"generator\": 5, \"wall\": 5}}, \"wild_2\": {\"width\": 15, \"height\": 10, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 1, \"converter\": 1, \"generator\": 5, \"wall\": 5}}, \"center\": {\"width\": 10, \"height\": 10, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 2, \"converter\": 5, \"generator\": 10, \"wall\": 20}}, \"base\": {\"width\": 15, \"height\": 15, \"border\": 1, \"objects\": {\"agent\": 5, \"altar\": 1, \"converter\": 3, \"generator\": 5, \"wall\": 5}}}}, \"kinship\": {\"team_size\": 1, \"team_reward\": 0}}",
+  "agent_cfg": "{\"_target_\": \"agent.metta_agent.MettaAgent\", \"observation_encoders\": {\"grid_obs\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 512, \"layers\": 4}, \"global_vars\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_action\": {\"feature_names\": [\"last_action_id\", \"last_action_val\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_reward\": {\"feature_names\": [\"last_reward\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"kinship\": {\"feature_names\": [\"kinship\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}}, \"fc\": {\"layers\": 3, \"output_dim\": 512}, \"decoder\": {\"_target_\": \"agent.decoder.Decoder\"}, \"core\": {\"rnn_type\": \"gru\", \"rnn_num_layers\": 1, \"rnn_size\": 512}}",
+  "command_line": "--experiment=p2.sf --train_dir=./train_dir/sample_factory --nonlinearity=elu --load_checkpoint_kind=latest --normalize_input=False --seed=0 --with_wandb=True --aux_loss_coeff=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 --batch_size=16384 --decorrelate_experience_max_seconds=150 --train_for_env_steps=9999999999999 --wandb_user=platypus --wandb_project=metta --rnn_type=gru --rnn_num_layers=1 --rnn_size=512 --env=GDY-MettaGrid --env_cfg={\"name\": \"GDY-MettaGrid\", \"_target_\": \"env.griddly.mettagrid.gym_env.MettaGridGymEnv\", \"max_action_value\": 10, \"hidden_features\": {\"grid_obs\": [\"agent:energy\", \"agent:hp\"]}, \"game\": {\"obs_width\": 11, \"obs_height\": 11, \"max_steps\": 5000, \"tile_size\": 16, \"num_agents\": 20, \"no_energy_steps\": 500, \"objects\": {\"agent\": {\"initial_energy\": 250, \"max_energy\": 250, \"max_inventory\": 5, \"freeze_duration\": 10, \"energy_reward\": false, \"hp\": 1, \"mortal\": false, \"upkeep\": {\"time\": 0, \"shield\": 1}, \"use_cost\": 0}, \"altar\": {\"hp\": 30, \"cooldown\": 2, \"use_cost\": 100}, \"converter\": {\"hp\": 30, \"cooldown\": 2, \"energy_output\": 50, \"use_cost\": 0}, \"generator\": {\"hp\": 30, \"cooldown\": 5, \"initial_resources\": 30, \"use_cost\": 0}, \"wall\": {\"density\": 0.01, \"hp\": 10}}, \"actions\": {\"move\": {\"cost\": 0}, \"rotate\": {\"cost\": 0}, \"jump\": {\"cost\": 3}, \"shield\": {\"cost\": 0}, \"drop\": {\"cost\": 1}, \"use\": {\"cost\": 0}, \"attack\": {\"cost\": 5, \"damage\": 5}}, \"map\": {\"layout\": {\"rooms_x\": 1, \"rooms_y\": 1, \"rooms\": [[\"base\", \"wild_1\", \"base\"], [\"wild_2\", \"center\", \"wild_2\"], [\"base\", \"wild_1\", \"base\"]]}, \"room\": {\"width\": 25, \"height\": 25, \"num_agents\": 5, \"objects\": {\"agent\": 5, \"altar\": 1, \"converter\": 3, \"generator\": 15, \"wall\": 10}}, \"wild_1\": {\"width\": 10, \"height\": 15, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 1, \"converter\": 1, \"generator\": 5, \"wall\": 5}}, \"wild_2\": {\"width\": 15, \"height\": 10, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 1, \"converter\": 1, \"generator\": 5, \"wall\": 5}}, \"center\": {\"width\": 10, \"height\": 10, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 2, \"converter\": 5, \"generator\": 10, \"wall\": 20}}, \"base\": {\"width\": 15, \"height\": 15, \"border\": 1, \"objects\": {\"agent\": 5, \"altar\": 1, \"converter\": 3, \"generator\": 5, \"wall\": 5}}}}, \"kinship\": {\"team_size\": 1, \"team_reward\": 0}} --agent_cfg={\"_target_\": \"agent.metta_agent.MettaAgent\", \"observation_encoders\": {\"grid_obs\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 512, \"layers\": 4}, \"global_vars\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_action\": {\"feature_names\": [\"last_action_id\", \"last_action_val\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_reward\": {\"feature_names\": [\"last_reward\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"kinship\": {\"feature_names\": [\"kinship\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}}, \"fc\": {\"layers\": 3, \"output_dim\": 512}, \"decoder\": {\"_target_\": \"agent.decoder.Decoder\"}, \"core\": {\"rnn_type\": \"gru\", \"rnn_num_layers\": 1, \"rnn_size\": 512}}",
+  "cli_args": {
+    "env": "GDY-MettaGrid",
+    "experiment": "p2.sf",
+    "train_dir": "./train_dir/sample_factory",
+    "seed": 0,
+    "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": "{\"name\": \"GDY-MettaGrid\", \"_target_\": \"env.griddly.mettagrid.gym_env.MettaGridGymEnv\", \"max_action_value\": 10, \"hidden_features\": {\"grid_obs\": [\"agent:energy\", \"agent:hp\"]}, \"game\": {\"obs_width\": 11, \"obs_height\": 11, \"max_steps\": 5000, \"tile_size\": 16, \"num_agents\": 20, \"no_energy_steps\": 500, \"objects\": {\"agent\": {\"initial_energy\": 250, \"max_energy\": 250, \"max_inventory\": 5, \"freeze_duration\": 10, \"energy_reward\": false, \"hp\": 1, \"mortal\": false, \"upkeep\": {\"time\": 0, \"shield\": 1}, \"use_cost\": 0}, \"altar\": {\"hp\": 30, \"cooldown\": 2, \"use_cost\": 100}, \"converter\": {\"hp\": 30, \"cooldown\": 2, \"energy_output\": 50, \"use_cost\": 0}, \"generator\": {\"hp\": 30, \"cooldown\": 5, \"initial_resources\": 30, \"use_cost\": 0}, \"wall\": {\"density\": 0.01, \"hp\": 10}}, \"actions\": {\"move\": {\"cost\": 0}, \"rotate\": {\"cost\": 0}, \"jump\": {\"cost\": 3}, \"shield\": {\"cost\": 0}, \"drop\": {\"cost\": 1}, \"use\": {\"cost\": 0}, \"attack\": {\"cost\": 5, \"damage\": 5}}, \"map\": {\"layout\": {\"rooms_x\": 1, \"rooms_y\": 1, \"rooms\": [[\"base\", \"wild_1\", \"base\"], [\"wild_2\", \"center\", \"wild_2\"], [\"base\", \"wild_1\", \"base\"]]}, \"room\": {\"width\": 25, \"height\": 25, \"num_agents\": 5, \"objects\": {\"agent\": 5, \"altar\": 1, \"converter\": 3, \"generator\": 15, \"wall\": 10}}, \"wild_1\": {\"width\": 10, \"height\": 15, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 1, \"converter\": 1, \"generator\": 5, \"wall\": 5}}, \"wild_2\": {\"width\": 15, \"height\": 10, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 1, \"converter\": 1, \"generator\": 5, \"wall\": 5}}, \"center\": {\"width\": 10, \"height\": 10, \"border\": 0, \"objects\": {\"agent\": 0, \"altar\": 2, \"converter\": 5, \"generator\": 10, \"wall\": 20}}, \"base\": {\"width\": 15, \"height\": 15, \"border\": 1, \"objects\": {\"agent\": 5, \"altar\": 1, \"converter\": 3, \"generator\": 5, \"wall\": 5}}}}, \"kinship\": {\"team_size\": 1, \"team_reward\": 0}}",
+    "agent_cfg": "{\"_target_\": \"agent.metta_agent.MettaAgent\", \"observation_encoders\": {\"grid_obs\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 512, \"layers\": 4}, \"global_vars\": {\"feature_names\": [], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_action\": {\"feature_names\": [\"last_action_id\", \"last_action_val\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"last_reward\": {\"feature_names\": [\"last_reward\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}, \"kinship\": {\"feature_names\": [\"kinship\"], \"normalize_features\": true, \"label_dim\": 4, \"output_dim\": 8, \"layers\": 2}}, \"fc\": {\"layers\": 3, \"output_dim\": 512}, \"decoder\": {\"_target_\": \"agent.decoder.Decoder\"}, \"core\": {\"rnn_type\": \"gru\", \"rnn_num_layers\": 1, \"rnn_size\": 512}}"
+  },
+  "git_hash": "791254b53964aa5fac266afe404e2350c892c122",
+  "git_repo_name": "https://github.com/daveey/metta.git",
+  "wandb_unique_id": "p2.sf_20240627_104843_316597"
+}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97f6125569a626ffe9531cb2748055d596ced299271bfab91007474cb22a791
+size 1620370