Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding

21 December 2021

Papers citing "Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding"

10 / 10 papers shown

Title
Safe Multi-Agent Reinforcement Learning via Shielding Ingy Elsayed-Aly Suda Bharadwaj Chris Amato Rüdiger Ehlers Ufuk Topcu Lu Feng 48 95 0 27 Jan 2021
Shielding Atari Games with Bounded Prescience Mirco Giacobbe Mohammadhosein Hasanbeig Daniel Kroening H. Wijk 41 23 0 20 Jan 2021
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones Brijen Thananjeyan Ashwin Balakrishna Suraj Nair Michael Luo K. Srinivasan M. Hwang Joseph E. Gonzalez Julian Ibarz Chelsea Finn Ken Goldberg OffRL 74 226 0 29 Oct 2020
Learning to be Safe: Deep RL with a Safety Critic K. Srinivasan Benjamin Eysenbach Sehoon Ha Jie Tan Chelsea Finn OffRL 73 144 0 27 Oct 2020
Conservative Safety Critics for Exploration Homanga Bharadhwaj Aviral Kumar Nicholas Rhinehart Sergey Levine Florian Shkurti Animesh Garg OffRL 85 139 0 27 Oct 2020
Mastering Atari with Discrete World Models Danijar Hafner Timothy Lillicrap Mohammad Norouzi Jimmy Ba DRL 95 852 0 05 Oct 2020
Safe Reinforcement Learning via Curriculum Induction M. Turchetta Andrey Kolobov S. Shah Andreas Krause Alekh Agarwal 37 92 0 22 Jun 2020
Dream to Control: Learning Behaviors by Latent Imagination Danijar Hafner Timothy Lillicrap Jimmy Ba Mohammad Norouzi VLM 111 1,354 0 03 Dec 2019
Learning Latent Dynamics for Planning from Pixels Danijar Hafner Timothy Lillicrap Ian S. Fischer Ruben Villegas David R Ha Honglak Lee James Davidson BDL 84 1,435 0 12 Nov 2018
Constrained Policy Optimization Joshua Achiam David Held Aviv Tamar Pieter Abbeel 110 1,322 0 30 May 2017