Various implementations disclosed herein include devices, systems, and methods for training of an action determining component of a computer character. In some implementations, actions are taken by the character in a 3D environment according to an action determining component of the character, where the character is rewarded or penalized for interactions associated with an object/concept in the 3D environment according to an assigned object/concept reward or penalty. In some implementations, the reward or the penalty assigned to the object/concept is modified, and the character is then rewarded or penalized for interactions associated with the object/concept according to the modified reward or the modified penalty. The action determining component of the character is trained using a reinforcement learning technique that accounts for rewards or penalties obtained by virtual character for interactions associated with the object/concept.