Upload new model run

models/LunarLander-v2/Sac/c1150cc28abe4baa987213a6bfded48d/README.md

@@ -0,0 +1,27 @@
+---
+model-index:
+- name: mock
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: mock
+      type: mock
+    metrics:
+    - type: mean_reward
+      value: mock +/- mock
+      name: mean_reward
+      verified: false
+tags:
+- reinforcement-learning
+- connect-four
+- pytorch
+- custom-implementation
+- generic
+run_info:
+  litrl:
+    version: !!python/module:litrl._version ''
+    repo_url: https://github.com/c-gohlke/LitRL.git
+    commit_hash: 1fb3129526c84808b59ccb0bad7d6cf03c13c19f
+---

models/LunarLander-v2/Sac/c1150cc28abe4baa987213a6bfded48d/config.yaml

@@ -0,0 +1,47 @@
+run_id: ${mlflow:null}
+tags:
+  model: ${model._target_}
+  env: ${model.cfg.env_id}
+  run_id: ${run_id}
+load_path: latest
+model:
+  _target_: litrl.model.sac.model.Sac
+  cfg:
+    seed: 123
+    val_env_seed: 10000
+    env_id: LunarLander-v2
+    env_fabric:
+      _target_: litrl.make
+      id: ${model.cfg.env_id}
+    val_env_fabric:
+      _target_: litrl.make
+      id: ${model.cfg.env_id}
+      val: true
+      render_each_n_episodes: 1
+    lr: 0.0001
+    gamma: 0.99
+    warm_start_steps: 10000.0
+    hidden_size: 64
+    n_hidden_layers: 2
+    epsilon: 0
+    tau: 0.005
+    target_entropy: null
+    buffer:
+      batch_size: 256
+      max_size: 1000000.0
+trainer:
+  _target_: lightning.Trainer
+  log_every_n_steps: 500
+  num_sanity_val_steps: 2
+  max_epochs: 500
+  limit_train_batches: 5000
+  logger:
+    _target_: litrl.common.logger.LitRLLogger
+    log_model: true
+    tags: ${tags}
+    run_id: ${run_id}
+  callbacks:
+  - _target_: litrl.common.huggingface.HuggingfaceCallback
+    mode: max
+    monitor: val_reward
+    filename: '{val_reward:.2f}-{step}'

models/LunarLander-v2/Sac/c1150cc28abe4baa987213a6bfded48d/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7b5ff7bcfd09d0fa37eaae9830af3599278eb7960eba053c4a5a7408886129
+size 37631

models/LunarLander-v2/Sac/c1150cc28abe4baa987213a6bfded48d/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75047aff371652523303e67fdcf902b3a7413255ce3993ee9b919879e78d9810
+size 440074

models/LunarLander-v2/Sac/c1150cc28abe4baa987213a6bfded48d/model_config.yaml

@@ -0,0 +1,23 @@
+root: !!python/object:litrl.schema.model.ModelConfigSchema
+  buffer: !!python/object:litrl.schema.model.BufferSchema
+    batch_size: 256
+    max_size: 1000000
+  env_fabric: !!python/object:litrl.schema.env.EnvSchema
+    _target_: litrl.make
+    id: LunarLander-v2
+    opponent: null
+    val: null
+  epsilon: 0.0
+  gamma: 0.99
+  hidden_size: 64
+  lr: 0.0001
+  n_hidden_layers: 2
+  seed: 123
+  target_entropy: null
+  tau: 0.005
+  val_env_fabric: !!python/object:litrl.schema.env.EnvSchema
+    _target_: litrl.make
+    id: LunarLander-v2
+    opponent: null
+    val: true
+  warm_start_steps: 10000

models/LunarLander-v2/Sac/c1150cc28abe4baa987213a6bfded48d/overrides.yaml

@@ -0,0 +1,2 @@
+- model=sac
+- env=lunar_lander

models/LunarLander-v2/Sac/results.yaml

@@ -5,6 +5,7 @@
 6f8b3f77c2d84815986ac12b78860732: 21.669418334960938
 796f8fe33b0344769264adafebc814a4: 984.3875732421875
 901f3f0af1174ea5a8d81b607beac4b1: 74.01914978027344
+c1150cc28abe4baa987213a6bfded48d: 138.86196899414062
 c417006c10294a3e8c66bfabb74b5dcc: -85.7021713256836
 dd63ef11719b45b1a3501ba0ae288223: 328.39361572265625
 e0ff8028956548f7b27df0d3f142d154: 1777.4488525390625