AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Lenient Learning in Independent-Learner Stochastic Cooperative Games

Ermo Wei, Sean Luke

JMLR 2016 · Multi-agent systems and games › Games and equilibria · approach: Learning in Markov games · 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 Boltzmann selection with Ranked Boltzmann (w=10) (ablation)LMRL2 · Gradient 1complete-policy count: 8407 -> 9983Improved
replace Boltzmann selection with Ranked Boltzmann (w=10) (ablation)LMRL2 · RO 3complete-policy count: 7332 -> 1739Hurt
replace Boltzmann selection with Ranked Boltzmann (w=10) (ablation)LMRL2 · RO 2complete-policy count: 9999 -> 5267Hurt
replace Boltzmann selection with Ranked Boltzmann (w=10) (ablation)LMRL2 · Climb-FScomplete-policy count: 9016 -> 9217Improved
add latching (temperature only heats up earlier states) (ablation)LMRL2 · Gradient 1complete-policy count: 8407 -> 7851Hurt
add latching (temperature only heats up earlier states) (ablation)LMRL2 · RO 3complete-policy count: 7332 -> 767Hurt
add latching (temperature only heats up earlier states) (ablation)LMRL2 · Heaven and Hellcorrect-policy count: 9991 -> 10000Improved
pair LMRL2 with Distributed Q-Learning instead of self-playLMRL2 · RO 1complete-policy count: 9368 -> 9998Improved
pair LMRL2 with Q-Learning instead of self-playLMRL2 · RO 2complete-policy count: 9999 -> 0Hurt
pair LMRL2 with Q-Learning instead of self-playLMRL2 · Climbcomplete-policy count: 9999 -> 27Hurt
lower learning rate to alpha=0.05LMRL2 · Gradient 1complete-policy count: 8407 -> 9207Improved
lower learning rate to alpha=0.05LMRL2 · RO 1complete-policy count: 9368 -> 9750Improved

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