AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation

Samuel Ainsworth, Matt Barnes, Siddhartha Srinivasa

NeurIPS 2019 · Reinforcement learning › MDPs and planning · approach: Rich-observation exploration · 0 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 e-stops based on expert visitation to Q-learningQ-learning · FrozenLake-v0sample efficiencyImproved
Add e-stops based on expert visitation to Q-learningQ-learning · FrozenLake-v0asymptotic rewardNo clear effect
Add e-stops based on expert visitationOne-step actor-critic · FrozenLake-v0sample efficiencyImproved
Add e-stops using expert-derived state boundsDDPG · Inverted pendulumconvergence speedImproved
Add e-stops using expert-derived state boundsDDPG · Inverted pendulumconvergence reliabilityImproved
Add e-stops using expert-derived state boundsDDPG · HalfCheetah-v3rewardImproved
Increase the fraction of low-visitation states replaced by e-stops (ablation)Value iteration · FrozenLake-v0convergence speedImproved
Increase the fraction of states removed until states crucial to reaching the goal are pruned (ablation)Value iteration with e-stops · FrozenLake-v0optimal policy rewardHurt
Replace the least-visited half of states with e-stops (ablation)Q-learning · FrozenLake-v0asymptotic rewardNo clear effect
Use e-stops learned from a suboptimal expert instead of an optimal expert (ablation)LearnedEStop · FrozenLake-v0e-stop policy performanceNo clear effect
Construct the support set from fewer expert roll-outs (ablation)LearnedEStop · FrozenLake-v0e-stop policy performanceNo clear effect

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