Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Visual Analogies between Atari Games for Studying Transfer Learning in RL
Doron Sobol, Lior Wolf, Yaniv Taigman
Feb 12, 2018 (modified: Feb 12, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract: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.
Enter your feedback below and we'll get back to you as soon as possible.