V Isual a Nalogies between a Tari G Ames for S Tudying T Ransfer L Earning in Rl

In this work, we ask the following question: can visual analogies, learned in an unsupervised way, be used in order to transfer knowledge between pairs of games and even play one game using an agent trained for another game. We attempt to answer this research question by creating visual analogies between a pair of games: a source game and a target game. For example, given a video frame in the target game, we map it to an analogous state in the source game and then attempt to play using a trained policy learned for the source game. We demonstrate convincing visual mapping between four pairs of games (eight mappings). These mappings are used to evaluate three transfer learning approaches. The code and models are available at https://github.com/doronsobol/ Visual_analogies_for_RL_transfer_Learning