22 citations · 31 across the 10 of their papers we have counts for
3 papers · 1 filter
Distributions In, Distributions Out: The Case for Soft-Label Training
Agamdeep Singh, Ashish Tiwari, Hosein Hasanbeig +1
Supervised classifiers output a distribution over classes but are typically trained against a single label obtained by collapsing multiple annotators into a majority vote. On tasks…
Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learning
Nabil Omi, Hosein Hasanbeig, Hiteshi Sharma +2
In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across…
Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis
Rohan Mitta, Hosein Hasanbeig, Jun Wang +3
This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during le…