AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Continuous-Time Fitted Value Iteration for Robust Policies

Michael Lutter, Boris Belousov, Shie Mannor, Dieter Fox, Animesh Garg, Jan Peters

TPAMI 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the adversary (robust rFVI instead of cFVI)DP value iteration · Simulated Cartpolereward: -024.2 -> -027.1Hurt
add the adversary (robust rFVI instead of cFVI)DP value iteration · Physical Cartpolereward: -143.7 -> -074.1Improved
add the adversary (robust rFVI instead of cFVI)DP value iteration · Physical Cartpolesuccess rate: 73.3 -> 100.0Improved
add the adversary (robust rFVI instead of cFVI)DP value iteration · Physical Furuta Pendulumreward: -082.1 -> -278.0Hurt
add the adversary (robust rFVI instead of cFVI)RTDP · Simulated Cartpole and Furuta pendulumsuccessHurt
use dynamic programming (uniform full-domain sampling) instead of RTDPcFVI · Physical Furuta Pendulumsuccess rate: 00.0 -> 100.0Improved
increase n-step horizon of value targetcFVI/rFVI · simulated systemsconvergence speedImproved
use very long n-step horizonscFVI/rFVI · Cartpole and Furuta pendulumconvergenceHurt
increase adversary strength alphaDP rFVI · simulated systemsrewardHurt
increase adversary strength alphaRTDP rFVI · simulated systemstask successHurt
use locally quadratic value network with sine/cosine transform instead of standard MLPcFVI · Cartpolelearning curveImproved
add domain randomization to PPO (uniform init)PPO · Physical Furuta Pendulumreward: -755.3 -> -080.6Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy