Batch RL (#238)

2025-12-17 19:20:19 +01:00 · 2019-03-19 18:07:09 +02:00
parent 4a8451ff02
commit e3c7e526c7
38 changed files with 1003 additions and 87 deletions
--- a/rl_coach/agents/agent_interface.py
+++ b/rl_coach/agents/agent_interface.py
@@ -173,3 +173,12 @@ class AgentInterface(object):
        :return: None
        """
        raise NotImplementedError("")
+    
+    def run_off_policy_evaluation(self) -> None:
+        """
+        Run off-policy evaluation estimators to evaluate the trained policy performance against a dataset.
+        Should only be implemented for off-policy RL algorithms.
+
+        :return: None
+        """
+        raise NotImplementedError("")