modify bullet/attn

4 年前 · d62f6b0a
--- a/Project/Assets/ML-Agents/Examples/Bullet/Demos/ExpertPush.demo.meta
+++ b/Project/Assets/ML-Agents/Examples/Bullet/Demos/ExpertPush.demo.meta
 fileFormatVersion: 2
 guid: 991552fb1f89746feb752872053e8fea
 ScriptedImporter:
-  fileIDToRecycleName:
-    11400000: Assets/ML-Agents/Examples/Bullet/Demos/ExpertPush.demo
+  internalIDToNameTable:
+  - first:
+      114: 11400000
+    second: Assets/ML-Agents/Examples/Bullet/Demos/ExpertPush.demo
+  serializedVersion: 2
  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
  assetBundleName: 
  assetBundleVariant: 
--- a/Project/Assets/ML-Agents/Examples/Bullet/Prefabs/BulletArea.prefab
+++ b/Project/Assets/ML-Agents/Examples/Bullet/Prefabs/BulletArea.prefab
  areaBounds:
    m_Center: {x: 0, y: 0, z: 0}
    m_Extent: {x: 0, y: 0, z: 0}
-  rad: 5
+  rad: 23
+  time: 0.2
+  dir: -1
  useVectorObs: 0
 --- !u!1 &7099812715628705112
 GameObject:
  areaBounds:
    m_Center: {x: 0, y: 0, z: 0}
    m_Extent: {x: 0, y: 0, z: 0}
-  rad: 1
+  rad: 23
+  time: 0.3
+  dir: 1
  useVectorObs: 0
 --- !u!1 &7564015931936126656
 GameObject:
  m_ProbeAnchor: {fileID: 0}
  m_LightProbeVolumeOverride: {fileID: 0}
  m_ScaleInLightmap: 1
+  m_ReceiveGI: 1
  m_PreserveUVs: 0
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
  m_ProbeAnchor: {fileID: 0}
  m_LightProbeVolumeOverride: {fileID: 0}
  m_ScaleInLightmap: 1
+  m_ReceiveGI: 1
  m_PreserveUVs: 0
  m_IgnoreNormalsForChartDetection: 0
  m_ImportantGI: 0
  m_Modification:
    m_TransformParent: {fileID: 7562565324271374322}
    m_Modifications:
-    - target: {fileID: 968348991679639438, guid: 7a515d80a9d5b4cfaba55aa066594016,
+    - target: {fileID: 5229809530250264056, guid: 7a515d80a9d5b4cfaba55aa066594016,
-      propertyPath: ground
-      value: 
-      objectReference: {fileID: 7564015931936126656}
-    - target: {fileID: 968348991679639438, guid: 7a515d80a9d5b4cfaba55aa066594016,
+      propertyPath: m_Name
+      value: DodgeAgentRaycast
+      objectReference: {fileID: 0}
+    - target: {fileID: 5229809530250264056, guid: 7a515d80a9d5b4cfaba55aa066594016,
-      propertyPath: area
-      value: 
-      objectReference: {fileID: 7565593112241766594}
+      propertyPath: m_IsActive
+      value: 0
+      objectReference: {fileID: 0}
    - target: {fileID: 2272550728573618168, guid: 7a515d80a9d5b4cfaba55aa066594016,
        type: 3}
      propertyPath: m_LocalPosition.x
      propertyPath: m_LocalEulerAnglesHint.z
      value: 0
      objectReference: {fileID: 0}
-    - target: {fileID: 5229809530250264056, guid: 7a515d80a9d5b4cfaba55aa066594016,
+    - target: {fileID: 968348991679639438, guid: 7a515d80a9d5b4cfaba55aa066594016,
-      propertyPath: m_Name
-      value: DodgeAgentRaycast
-      objectReference: {fileID: 0}
-    - target: {fileID: 5229809530250264056, guid: 7a515d80a9d5b4cfaba55aa066594016,
+      propertyPath: ground
+      value: 
+      objectReference: {fileID: 7564015931936126656}
+    - target: {fileID: 968348991679639438, guid: 7a515d80a9d5b4cfaba55aa066594016,
-      propertyPath: m_IsActive
-      value: 0
-      objectReference: {fileID: 0}
+      propertyPath: area
+      value: 
+      objectReference: {fileID: 7565593112241766594}
    m_RemovedComponents: []
  m_SourcePrefab: {fileID: 100100000, guid: 7a515d80a9d5b4cfaba55aa066594016, type: 3}
 --- !u!4 &4270948751059092865 stripped
  m_Modification:
    m_TransformParent: {fileID: 7562565324271374322}
    m_Modifications:
-    - target: {fileID: 968348991679639438, guid: 16266ae2c040142b1a996878d94ec3fb,
+    - target: {fileID: 5229809530250264056, guid: 16266ae2c040142b1a996878d94ec3fb,
-      propertyPath: ground
-      value: 
-      objectReference: {fileID: 7564015931936126656}
-    - target: {fileID: 968348991679639438, guid: 16266ae2c040142b1a996878d94ec3fb,
+      propertyPath: m_Name
+      value: DodgeAgent
+      objectReference: {fileID: 0}
+    - target: {fileID: 5229809530250264056, guid: 16266ae2c040142b1a996878d94ec3fb,
-      propertyPath: area
-      value: 
-      objectReference: {fileID: 7565593112241766594}
+      propertyPath: m_IsActive
+      value: 1
+      objectReference: {fileID: 0}
    - target: {fileID: 2272550728573618168, guid: 16266ae2c040142b1a996878d94ec3fb,
        type: 3}
      propertyPath: m_LocalPosition.x
      propertyPath: m_LocalEulerAnglesHint.z
      value: 0
      objectReference: {fileID: 0}
-    - target: {fileID: 5229809530250264056, guid: 16266ae2c040142b1a996878d94ec3fb,
+    - target: {fileID: 968348991679639438, guid: 16266ae2c040142b1a996878d94ec3fb,
-      propertyPath: m_Name
-      value: DodgeAgent
-      objectReference: {fileID: 0}
-    - target: {fileID: 5229809530250264056, guid: 16266ae2c040142b1a996878d94ec3fb,
+      propertyPath: ground
+      value: 
+      objectReference: {fileID: 7564015931936126656}
+    - target: {fileID: 968348991679639438, guid: 16266ae2c040142b1a996878d94ec3fb,
-      propertyPath: m_IsActive
-      value: 1
-      objectReference: {fileID: 0}
+      propertyPath: area
+      value: 
+      objectReference: {fileID: 7565593112241766594}
    m_RemovedComponents:
    - {fileID: 9204493211719777360, guid: 16266ae2c040142b1a996878d94ec3fb, type: 3}
  m_SourcePrefab: {fileID: 100100000, guid: 16266ae2c040142b1a996878d94ec3fb, type: 3}
  m_Modification:
    m_TransformParent: {fileID: 7562565324271374322}
    m_Modifications:
-    - target: {fileID: 114291266114270340, guid: 6693afcd33b8842fba88da9b967315ff,
+    - target: {fileID: 5229809530250264056, guid: 6693afcd33b8842fba88da9b967315ff,
-      propertyPath: ChannelDepth.Array.size
-      value: 1
+      propertyPath: m_Name
+      value: GridDodgeAgent
-    - target: {fileID: 114291266114270340, guid: 6693afcd33b8842fba88da9b967315ff,
+    - target: {fileID: 5229809530250264056, guid: 6693afcd33b8842fba88da9b967315ff,
-      propertyPath: ChannelDepth.Array.data[0]
-      value: 1
+      propertyPath: m_IsActive
+      value: 0
-    - target: {fileID: 968348991679639438, guid: 6693afcd33b8842fba88da9b967315ff,
-        type: 3}
-      propertyPath: ground
-      value: 
-      objectReference: {fileID: 7564015931936126656}
-    - target: {fileID: 968348991679639438, guid: 6693afcd33b8842fba88da9b967315ff,
-        type: 3}
-      propertyPath: area
-      value: 
-      objectReference: {fileID: 7565593112241766594}
    - target: {fileID: 2272550728573618168, guid: 6693afcd33b8842fba88da9b967315ff,
        type: 3}
      propertyPath: m_LocalPosition.x
      propertyPath: m_LocalEulerAnglesHint.z
      value: 0
      objectReference: {fileID: 0}
-    - target: {fileID: 5229809530250264056, guid: 6693afcd33b8842fba88da9b967315ff,
+    - target: {fileID: 968348991679639438, guid: 6693afcd33b8842fba88da9b967315ff,
+        type: 3}
+      propertyPath: ground
+      value: 
+      objectReference: {fileID: 7564015931936126656}
+    - target: {fileID: 968348991679639438, guid: 6693afcd33b8842fba88da9b967315ff,
-      propertyPath: m_Name
-      value: GridDodgeAgent
+      propertyPath: area
+      value: 
+      objectReference: {fileID: 7565593112241766594}
+    - target: {fileID: 114291266114270340, guid: 6693afcd33b8842fba88da9b967315ff,
+        type: 3}
+      propertyPath: ChannelDepth.Array.size
+      value: 1
-    - target: {fileID: 5229809530250264056, guid: 6693afcd33b8842fba88da9b967315ff,
+    - target: {fileID: 114291266114270340, guid: 6693afcd33b8842fba88da9b967315ff,
-      propertyPath: m_IsActive
-      value: 0
+      propertyPath: ChannelDepth.Array.data[0]
+      value: 1
      objectReference: {fileID: 0}
    m_RemovedComponents: []
  m_SourcePrefab: {fileID: 100100000, guid: 6693afcd33b8842fba88da9b967315ff, type: 3}
--- a/Project/Assets/ML-Agents/Examples/Bullet/Scripts/BulletAgent.cs
+++ b/Project/Assets/ML-Agents/Examples/Bullet/Scripts/BulletAgent.cs
    [HideInInspector]
    public Bounds areaBounds;
    public float rad;
+    public float time;
+    public float dir;

    BulletSettings m_BulletSettings;


    public void FixedUpdate()
    {
-        if (Time.time > m_BulletTime + 0.03f)
+        if (Time.time > m_BulletTime + time)
-            var r = Random.Range(0f, 360f);
-            var ra = Random.Range(0, 2);
-            var dir = -1f;
-            if (ra == 1)
-            {
-                dir = 1f;
-            }
-            var angle = dir * (5f * Mathf.PI/ 180f);
+            //var r = Random.Range(0f, 360f);
+
+            var angle = dir * (30f * Mathf.PI/ 180f);
-            Quaternion rotation = Quaternion.Euler(0, r, 0);
-            //Quaternion rotation = Quaternion.LookRotation(m_center - pos);
+            //Quaternion rotation = Quaternion.Euler(0, r, 0);
+            Quaternion rotation = Quaternion.LookRotation(m_center - pos);
            var ob = Instantiate(m_BulletRb, pos, rotation, area.transform);
            m_currX = x;
            m_currZ = z;
--- a/Project/Assets/ML-Agents/Examples/Bullet/Scripts/DodgeAgent.cs
+++ b/Project/Assets/ML-Agents/Examples/Bullet/Scripts/DodgeAgent.cs
    {
        if (collision.gameObject.CompareTag("bullet") || collision.gameObject.CompareTag("wall"))
        {
-            SetReward(0f);
+            SetReward(-1f);
            EndEpisode();
        }
    }
--- a/config/ppo/Bullet.yaml
+++ b/config/ppo/Bullet.yaml
  Dodge:
    trainer_type: ppo
    hyperparameters:
-      batch_size: 1024
-      buffer_size: 10240
+      batch_size: 4096
+      buffer_size: 40960
-      learning_rate_schedule: linear
+      learning_rate_schedule: constant
-      normalize: true
+      normalize: false
      hidden_units: 128
      num_layers: 2
      vis_encode_type: simple
        strength: 1.0
    keep_checkpoints: 5
-    max_steps: 5000000
+    max_steps: 50000000
    time_horizon: 64
    summary_freq: 10000
    threaded: true
--- a/ml-agents/mlagents/trainers/torch/networks.py
+++ b/ml-agents/mlagents/trainers/torch/networks.py
        self.use_fc = False

        if not self.use_fc:
-            emb_size = 64
+            emb_size = 32
-                x_self_size=64,
-                entities_sizes=[64],  # hard coded, 4 obs per entity
+                x_self_size=32,
+                entities_sizes=[32],  # hard coded, 4 obs per entity
-            #self.self_embedding = LinearEncoder(6, 2, 64)
-            #self.obs_embeding = LinearEncoder(4, 2, 64)
-            # self.self_and_obs_embedding = LinearEncoder(64 + 64, 1, 64)
-            # self.dense_after_attention = LinearEncoder(64, 1, 64)
+            #self.self_embedding = LinearEncoder(6, 2, 32)
+            #self.obs_embeding = LinearEncoder(4, 2, 32)
+            # self.self_and_obs_embedding = LinearEncoder(32 + 32, 1, 32)
+            # self.dense_after_attention = LinearEncoder(32, 1, 32)
-            self.embedding_encoder = LinearEncoder(10, 2, 64)
+            #self.embedding_encoder = LinearEncoder(10, 2, 32)
+            self.embedding_encoder = LinearEncoder(4, 2, 32)
-                emb_size, network_settings.num_layers - 1, self.h_size
+                emb_size + 6, network_settings.num_layers - 1, self.h_size
            )
        else:
            self.linear_encoder = LinearEncoder(
        if not self.use_fc:
            #x_self = self.embedding(processed_vec)
            var_len_input = vis_inputs[0].reshape(-1, 20, 4)
-            expanded_self = processed_vec.reshape(-1, 1, 6)
-            expanded_self = torch.cat([expanded_self] * 20, dim=1)
-            concat_ent = torch.cat([expanded_self, var_len_input], dim=-1)
-            processed_var_len_input = self.embedding_encoder(concat_ent)
+            #expanded_self = processed_vec.reshape(-1, 1, 6)
+            #expanded_self = torch.cat([expanded_self] * 20, dim=1)
+            #concat_ent = torch.cat([expanded_self, var_len_input], dim=-1)
+            #processed_var_len_input = self.embedding_encoder(concat_ent)
+            processed_var_len_input = self.embedding_encoder(var_len_input)
            output = self.transformer(processed_var_len_input, self.masking_module([var_len_input]))
            #output = self.transformer(x_self, [processed_var_len_input], self.masking_module([var_len_input]))

            #     1 - key_mask, dim=1, keepdim=True
            # ) + 0.001 )   # average pooling

-            #encoding = self.linear_encoder(torch.cat([output, x_self], dim=1))
-            encoding = self.linear_encoder(output)
+            encoding = self.linear_encoder(torch.cat([output, processed_vec], dim=1))
+            #encoding = self.linear_encoder(output)
        else:
            encoding = self.linear_encoder(torch.cat([vis_inputs[0].reshape(-1, 80), processed_vec], dim=1))

--- a/Project/Assets/ML-Agents/Examples/Bullet/Scripts/.BulletAgent.cs.swp
+++ b/Project/Assets/ML-Agents/Examples/Bullet/Scripts/.BulletAgent.cs.swp