Rainbow DQN agent (WIP - still missing dueling and n-step) + adding support for Prioritized ER for C51

rl_coach/architectures/tensorflow_components/heads/rainbow_dqn_head.py

@@ -0,0 +1,44 @@
+#
+# Copyright (c) 2017 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import tensorflow as tf
+
+from rl_coach.architectures.tensorflow_components.architecture import Dense
+from rl_coach.base_parameters import AgentParameters
+from rl_coach.spaces import SpacesDefinition
+
+from rl_coach.architectures.tensorflow_components.heads.head import Head, HeadParameters
+from rl_coach.core_types import QActionStateValue
+
+
+class RainbowQHeadParameters(HeadParameters):
+    def __init__(self, activation_function: str ='relu', name: str='rainbow_q_head_params', dense_layer=Dense):
+        super().__init__(parameterized_class=RainbowQHead, activation_function=activation_function, name=name,
+                         dense_layer=dense_layer)
+
+
+class RainbowQHead():
+    def __init__(self, agent_parameters: AgentParameters, spaces: SpacesDefinition, network_name: str,
+                 head_idx: int = 0, loss_weight: float = 1., is_local: bool = True, activation_function: str ='relu',
+                 dense_layer=Dense):
+        super().__init__(agent_parameters, spaces, network_name, head_idx, loss_weight, is_local, activation_function,
+                         dense_layer=dense_layer)
+        self.name = 'rainbow_dqn_head'
+        self.num_actions = len(self.spaces.action.actions)
+        self.return_type = QActionStateValue
+
+    def _build_module(self, input_layer):
+        pass