Is there higher order reinforcement learning, that can not only find rewards (and hence optimal policy), bet that can also find the necessity to introduce new states and actions to better model the available data? Reinforcement learning that can act in previously unknown situations (new states eventually) or that can discover/acquire previously unknown faculties (new actions eventually)? Maybe one can consider genetic programming for the generation/maintenance of the state and action instances and then can one restart again and again RL process in lifelong learning setting?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.