setup proxy luis

ymahlau · Dec 2, 2023 · 0b0f2f0 · 0b0f2f0
1 parent 6ee302d
commit 0b0f2f0
Show file tree

Hide file tree

Showing 32 changed files with 6,122 additions and 239 deletions.
diff --git a/config/cfg_luis_proxy_aa_0.yaml b/config/cfg_luis_proxy_aa_0.yaml
@@ -26,7 +26,7 @@ data:
       eval_rate_sec: 60
       num_episodes:
       - 100
-      - 20
+      - 2
       prevent_draw: false
       save_checkpoints: false
       self_play: true
@@ -151,7 +151,7 @@ data:
   merge_inference_update_gpu: false
   net_cfg:
     __module__: src.network.resnet
-    __name__: OvercookedResNetConfig5x5
+    __name__: OvercookedResNetConfig9x9
     data:
       activation_type:
         __module__: src.network.utils
@@ -173,8 +173,13 @@ data:
         - 3
         - 1
         - 1
-      - - 128
+      - - 64
+        - 1
+        - 3
+        - 0
         - 1
+      - - 128
+        - 2
         - 3
         - 1
         - 1
@@ -367,7 +372,7 @@ data:
             data:
               active_wait_time: 0.05
               init_temperatures: null
-              max_clip_value: .inf
+              max_clip_value: 30
               min_clip_value: -.inf
               policy_prediction: true
               random_symmetry: false

diff --git a/config/cfg_luis_proxy_aa_1.yaml b/config/cfg_luis_proxy_aa_1.yaml
@@ -26,7 +26,7 @@ data:
       eval_rate_sec: 60
       num_episodes:
       - 100
-      - 20
+      - 2
       prevent_draw: false
       save_checkpoints: false
       self_play: true
@@ -151,7 +151,7 @@ data:
   merge_inference_update_gpu: false
   net_cfg:
     __module__: src.network.resnet
-    __name__: OvercookedResNetConfig5x5
+    __name__: OvercookedResNetConfig9x9
     data:
       activation_type:
         __module__: src.network.utils
@@ -161,7 +161,97 @@ data:
         __module__: src.network.vision_net
         __name__: EquivarianceType
         value: NONE
-      game_cfg: null
+      game_cfg:
+        __module__: src.game.overcooked.config
+        __name__: AsymmetricAdvantageOvercookedConfig
+        data:
+          board:
+          - - 1
+            - 1
+            - 1
+            - 1
+            - 1
+            - 1
+            - 1
+            - 1
+            - 1
+          - - 3
+            - 0
+            - 1
+            - 5
+            - 1
+            - 3
+            - 1
+            - 0
+            - 5
+          - - 1
+            - 0
+            - 0
+            - 0
+            - 4
+            - 0
+            - 0
+            - 0
+            - 1
+          - - 1
+            - 0
+            - 0
+            - 0
+            - 4
+            - 0
+            - 0
+            - 0
+            - 1
+          - - 1
+            - 1
+            - 1
+            - 2
+            - 1
+            - 2
+            - 1
+            - 1
+            - 1
+          cooking_time: 20
+          flat_obs: false
+          h: 5
+          horizon: 400
+          num_actions: 6
+          num_players: 2
+          reward_cfg:
+            __module__: src.game.overcooked.config
+            __name__: OvercookedRewardConfig
+            data:
+              dish_pickup: 3
+              placement_in_pot: 3
+              soup_delivery: 20
+              soup_pickup: 5
+              start_cooking: 3
+          reward_scaling_factor: 1
+          single_temperature_input: true
+          start_pos:
+            __module__: src.misc.serialization
+            __name__: TupleWrapper
+            data:
+              data:
+              - __module__: src.misc.serialization
+                __name__: TupleWrapper
+                data:
+                  data:
+                  - 6
+                  - 2
+                  - 0
+                  - 0
+              - __module__: src.misc.serialization
+                __name__: TupleWrapper
+                data:
+                  data:
+                  - 1
+                  - 3
+                  - 0
+                  - 0
+          temperature_input: true
+          unstuck_behavior: false
+          w: 9
       layer_specs:
       - - 32
         - 3
@@ -173,9 +263,14 @@ data:
         - 3
         - 1
         - 1
-      - - 128
+      - - 64
         - 1
         - 3
+        - 0
+        - 1
+      - - 128
+        - 2
+        - 3
         - 1
         - 1
       - - 256
@@ -367,7 +462,7 @@ data:
             data:
               active_wait_time: 0.05
               init_temperatures: null
-              max_clip_value: .inf
+              max_clip_value: 30
               min_clip_value: -.inf
               policy_prediction: true
               random_symmetry: false