Unity-Technologies · awjuliani · Jul 23, 2020 · Jul 20, 2020 · Jul 20, 2020 · Jul 21, 2020
diff --git a/ml-agents/mlagents/trainers/components/reward_signals/__init__.py b/ml-agents/mlagents/trainers/components/reward_signals/__init__.py
@@ -23,7 +23,7 @@ def __init__(self, policy: TFPolicy, settings: RewardSignalSettings):
         """
         Initializes a reward signal. At minimum, you must pass in the policy it is being applied to,
         the reward strength, and the gamma (discount factor.)
-        :param policy: The Policy object (e.g. NNPolicy) that this Reward Signal will apply to.
+        :param policy: The Policy object (e.g. TFPolicy) that this Reward Signal will apply to.
         :param settings: Settings parameters for this Reward Signal, including gamma and strength.
         :return: A RewardSignal object.
         """

diff --git a/ml-agents/mlagents/trainers/policy/nn_policy.py b/ml-agents/mlagents/trainers/policy/nn_policy.py