AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Self-Imitation Learning via Generalized Lower Bound Q-learning

Yunhao Tang

NeurIPS 2020 · Learning theory and algorithms › Sample complexity · approach: Robust and surrogate-loss learning bounds · 13 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
Use 5-step generalized SIL instead of 5-step TD3TD3 · DMWalkerRun, DMWalkerStand, DMWalkerWalk, DMCheetahRun, Ant, Ant(B), HalfCheetah(B)performance: 246 ± 49 -> 642 ± 107; 749 ± 150 -> 979 ± 2; 925 ± 10 -> 731 ± 151; 553 ± 92 -> 830 ± 36; 1058 ± 281 -> 4123 ± 364; 2920Improved
Use 5-step generalized SIL instead of 5-step TD3TD3 · HalfCheetahperformance: 6178 ± 151 -> 8246 ± 784Hurt
Use n=5 generalized SIL rather than n=1 generalized SIL (ablation)TD3 · DMWalkerRun, DMWalkerStand, DMWalkerWalk, DMCheetahRun, Ant, HalfCheetah, Ant(B), HalfCheetah(B)performance: 500 ± 138 -> 642 ± 107; 899 ± 55 -> 979 ± 2; 601 ± 108 -> 731 ± 151; 702 ± 72 -> 830 ± 36; 3166 ± 390 -> 4123 ± 364; 104Mixed
Use 5-step generalized SIL rather than return-based SIL (n=infinity) (ablation)TD3 · DMWalkerRun, DMWalkerStand, DMWalkerWalk, DMCheetahRun, Ant, HalfCheetah, Ant(B), HalfCheetah(B)performance: 320 ± 111 -> 642 ± 107; 748 ± 143 -> 979 ± 2; 398 ± 203 -> 731 ± 151; 655 ± 59 -> 830 ± 36; 3787 ± 411 -> 4123 ± 364; 83Mixed
Remove IS corrections from prioritized replay (ablation)Generalized SIL n=5 with TD3 · DMWalkerRun, DMWalkerStand, DMWalkerWalk, DMCheetahRun, Ant, HalfCheetah, Ant(B), HalfCheetah(B)performance: 642 ± 107 -> 675 ± 15; 979 ± 2 -> 947 ± 18; 731 ± 151 -> 622 ± 197; 830 ± 36 -> 597 ± 64; 4123 ± 364 -> 3059 ± 360; 8246Mixed
Add prioritized sampling (ablation)Generalized SIL n=5 with TD3 · DMWalkerRun, DMWalkerStand, DMCheetahRun, HalfCheetah, HalfCheetah(B)performance: 424 ± 127 -> 642 ± 107; 634 ± 184 -> 979 ± 2; 505 ± 182 -> 830 ± 36; 8927 ± 596 -> 8246 ± 784; 2284 ± 85 -> 2619 ± 129Improved
Add prioritized sampling (ablation)Generalized SIL n=5 with TD3 · DMWalkerWalk, Ant, Ant(B)performance: 766 ± 103 -> 731 ± 151; 4358 ± 496 -> 4123 ± 364; 2910 ± 88 -> 2954 ± 54Mixed
Use generalized SIL n=5 rather than return-based SILPPO · Ant and Humanoid delayed-reward tasksperformanceMixed
Apply generalized SIL n=5 instead of plain PPOPPO · OpenAI Gym delayed-reward tasksperformanceImproved
Add generalized SIL n=5 to DDPGDDPG · Continuous-control tasksperformanceNo clear effect
Use 5-step generalized SIL rather than n=1 generalized SIL (ablation)TD3 · Deterministic continuous-control tasksperformanceImproved
Use return-based SIL (n=infinity) rather than 5-step generalized SIL (ablation)TD3 · Deterministic continuous-control tasksoptimization speedHurt

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