AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Expressive Temporal Specifications for Reward Monitoring

Omar Adalat, Francesco Belardinelli

AAAI 2026 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 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
replace Boolean monitor with quantitative LTLf[F] monitorPPO · Acrobottask completion (%): 4.84% -> 94.77%Improved
replace Boolean monitor with quantitative LTLf[F] monitorPPO · Pendulumtask completion (%): 45.03% -> 72.11%Improved
replace Boolean monitor with quantitative LTLf[F] monitorPPO · Bipedal Walkertask completion (%): 7.43% -> 14.43%Improved
replace Boolean monitor with quantitative LTLf[F] monitorPPO · Cartpole, Mountain Car, Lunar Landertask completion (%): 30.92% -> 33.34% (Cartpole); 37.04% -> 42.28% (Mountain Car); 43.44% -> 45.61% (Lunar Lander)Improved
replace Boolean monitor with quantitative monitorQ-learning · Frozen Laketask completion (%): 62.16% -> 58.96%Hurt
replace Boolean monitor with quantitative monitorQ-learning · Cliff Walking and Island Navigationtask completion (%): 84.38% -> 84.95% (Cliff Walking); 76.37% -> 76.72% (Island Navigation)No clear effect
replace Boolean monitor with quantitative monitorQ-learning · Taxitask completion (%): 46.50% -> 52.76%Improved
replace Boolean monitor with quantitative monitorQ-learning · Conveyor Belt and Sokobantask completion (%): 27.1% -> 28.70% (Conveyor Belt); 52.00% -> 53.15% (Sokoban)No clear effect
use quantitative monitor instead of handcrafted rewardQ-learning · Sokobantask completion (%): 50.23% -> 53.15%Improved
use quantitative monitor instead of handcrafted rewardPPO · Mountain Cartask completion (%): 39.82% -> 42.28%Improved
use quantitative monitor instead of handcrafted rewardPPO and Q-learning · Acrobot, Cartpole, Taxi, Island Navigation, Conveyor Belttask completion (%): 99.07% -> 94.77% (Acrobot); 71.19% -> 52.76% (Taxi); 96.81% -> 76.72% (Island Navigation)Hurt
use quantitative monitor instead of Boolean monitorQ-learning · Frozen Lake and Cliff Walkingconvergence time (s): 0.03 -> 0.01 (Frozen Lake); 0.04 -> 0.003 (Cliff Walking)Improved

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