AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Reinforcement Learning with a Terminator

Guy Tennenholtz, Nadav Merlis, Lior Shani, Shie Mannor, Uri Shalit, Gal Chechik, Assaf Hallak, Gal Dalal

NeurIPS 2022 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 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
remove optimism (use ensemble mean) (ablation)TermPG · MinAtar Breakoutmean total reward: 8.2 -> 1.3Hurt
remove optimism (use ensemble mean) (ablation)TermPG · MinAtar Space Invadersmean total reward: 9.7 -> 5.2Hurt
remove optimism (use ensemble mean) (ablation)TermPG · Backseat Driver coin avoidancemean total reward: 8.7 -> 7.8Mixed
remove dynamic discount factor (gamma 0.99) (ablation)TermPG · MinAtar Breakoutmean total reward: 8.2 -> 0.5Hurt
remove dynamic discount factor (gamma 0.99) (ablation)TermPG · Backseat Driver human terminationmean total reward: 8.3 -> 5.9Hurt
remove dynamic discount factor (gamma 0.99) (ablation)TermPG · MinAtar Space Invadersmean total reward: 9.7 -> 4.4Hurt
replace min-ensemble optimism with mean minus alpha*std (ablation)TermPG · MinAtar Space Invadersmean total reward: 9.7 -> 2.8Hurt
replace min-ensemble optimism with mean minus alpha*std (ablation)TermPG · MinAtar Breakoutmean total reward: 8.2 -> 10.9Improved
replace min-ensemble optimism with mean minus alpha*std (ablation)TermPG · Backseat Driver coin avoidancemean total reward: 8.7 -> 7.6Hurt
window misspecification x0.5 (ablation)TermPG · MinAtar Space Invadersmean total reward: 9.7 -> 9.7No clear effect
window misspecification x2 (ablation)TermPG · MinAtar Breakoutmean total reward: 8.2 -> 10.3Mixed
add termination reward-shaping penalty to TermPGTermPG · MinAtar Breakoutmean total reward: 8.2 -> 5.1Hurt

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