Upload policy weights, train config and readme

README.md

@@ -1,5 +1,5 @@
 ---
-datasets: spirosperos/grid-position-dataset
+datasets: spirosperos/grid-position-prediction
 library_name: lerobot
 license: apache-2.0
 model_name: sac

config.json

@@ -3,7 +3,7 @@
     "n_obs_steps": 1,
     "normalization_mapping": {
         "VISUAL": "MEAN_STD",
-        "ACTION": "MIN_MAX"
+        "ACTION": "IDENTITY"
     },
     "input_features": {
         "observation.image": {
@@ -98,9 +98,9 @@
         "activate_final": true
     },
     "policy_kwargs": {
-        "use_tanh_squash": true,
+        "use_tanh_squash": false,
         "std_min": 1e-05,
-        "std_max": 10.0,
+        "std_max": 5.0,
         "init_final": 0.05
     },
     "discrete_critic_network_kwargs": {
@@ -113,8 +113,8 @@
     },
     "actor_learner_config": {
         "learner_host": "127.0.0.1",
-        "learner_port": 60000,
-        "policy_parameters_push_frequency": 1,
+        "learner_port": 50053,
+        "policy_parameters_push_frequency": 0,
         "queue_get_timeout": 2.0
     },
     "concurrency": {

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e167ec051a8d643e123c321984eee6d332e0aa54467af10146843363733a10b
-size 22659140
+oid sha256:212c99227350f091ca67a635aaa39f1455ce80df635175d47b8a649f24c7730b
+size 22658540

train_config.json

@@ -1,7 +1,7 @@
 {
     "dataset": {
-        "repo_id": "spirosperos/grid-position-dataset",
-        "root": "/home/nikola/lerobot_spes/examples/grid_hil_serl/recording_grid_position_lerobot_001",
+        "repo_id": "spirosperos/grid-position-prediction",
+        "root": "/home/nikola/lerobot_spes/recording_grid_position_lerobot",
         "episodes": null,
         "image_transforms": {
             "enable": false,
@@ -126,7 +126,7 @@
         "n_obs_steps": 1,
         "normalization_mapping": {
             "VISUAL": "MEAN_STD",
-            "ACTION": "MIN_MAX"
+            "ACTION": "IDENTITY"
         },
         "input_features": {
             "observation.image": {
@@ -221,9 +221,9 @@
             "activate_final": true
         },
         "policy_kwargs": {
-            "use_tanh_squash": true,
+            "use_tanh_squash": false,
             "std_min": 1e-05,
-            "std_max": 10.0,
+            "std_max": 5.0,
             "init_final": 0.05
         },
         "discrete_critic_network_kwargs": {
@@ -236,8 +236,8 @@
         },
         "actor_learner_config": {
             "learner_host": "127.0.0.1",
-            "learner_port": 60000,
-            "policy_parameters_push_frequency": 1,
+            "learner_port": 50053,
+            "policy_parameters_push_frequency": 0,
             "queue_get_timeout": 2.0
         },
         "concurrency": {
@@ -246,7 +246,7 @@
         },
         "use_torch_compile": false
     },
-    "output_dir": "outputs/train/2025-10-22/12-14-01_grid_position",
+    "output_dir": "outputs/train/2025-10-30/13-19-54_grid_position",
     "job_name": "grid_position",
     "resume": false,
     "seed": 1000,