A
Aviv Tamar
Researcher at Technion – Israel Institute of Technology
Publications - 111
Citations - 7986
Aviv Tamar is an academic researcher from Technion – Israel Institute of Technology. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 31, co-authored 97 publications receiving 5310 citations. Previous affiliations of Aviv Tamar include Cornell University & Facebook.
Papers
More filters
Posted Content
Validate on Sim, Detect on Real - Model Selection for Domain Randomization.
TL;DR: In this article, an out-of-distribution detection (OOD) technique is used to evaluate the performance of the policies without running them in the real world, using a predefined set of real world data.
Posted Content
Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder
Tal Daniel,Aviv Tamar +1 more
TL;DR: In this article, a modified introspective variational autoencoder (IntroVAE) is proposed, which replaces the hinge-loss terms with a smooth exponential loss on generated samples.
Journal Article
Deep Bribe: Predicting the Rise of Bribery in Blockchain Mining with Deep RL
TL;DR: In this paper , the authors use deep reinforcement learning to analyze how a rational miner performs selfish mining by deviating from the protocol to maximize revenue when petty compliant miners are present, and they find that a selfish miner can exploit the selfish miners to increase her revenue by bribing them.
Proceedings ArticleDOI
Robust 2D Assembly Sequencing via Geometric Planning with Learned Scores
TL;DR: In this article, a convolutional neural network is used to map assembly operations, given as an image pair of the subassemblies before and after they are mated, to a robustness score, which is used within a planner to quickly prune out motions that are not robust.
Journal ArticleDOI
TGRL: An Algorithm for Teacher Guided Reinforcement Learning
TL;DR: Teacher Guided Reinforcement Learning (TGRL) as mentioned in this paper adjusts the importance of teacher supervision by comparing the agent's performance to the counterfactual scenario of the agent learning without teacher supervision.