Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models

8 June 2020

Papers citing "Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models"

9 / 9 papers shown

Title
Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning Bradley Burega John D. Martin Luke Kapeluck Michael Bowling 40 0 0 27 Jun 2024
The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning Anya Sims Cong Lu Yee Whye Teh OffRL 35 3 0 19 Feb 2024
A Tractable Inference Perspective of Offline RL Xuejie Liu Hoang Trung-Dung Guy Van den Broeck Yitao Liang OffRL 36 1 0 31 Oct 2023
Predictable MDP Abstraction for Unsupervised Model-Based RL Seohong Park Sergey Levine 26 9 0 08 Feb 2023
Goal-Space Planning with Subgoal Models Chun-Ping Lo Kevin Roice Parham Mohammad Panahi Scott M. Jordan Adam White Gábor Mihucz Farzane Aminmansour Martha White 29 5 0 06 Jun 2022
Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning L. Pullum 26 2 0 22 Mar 2022
Forethought and Hindsight in Credit Assignment Veronica Chelu Doina Precup H. V. Hasselt 22 25 0 26 Oct 2020
Selective Dyna-style Planning Under Limited Model Capacity Zaheer Abbas Samuel Sokota Erin J. Talvitie Martha White 37 32 0 05 Jul 2020
Off-Policy Actor-Critic T. Degris Martha White R. Sutton OffRL CML 163 220 0 22 May 2012