AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Influencing Long-Term Behavior in Multiagent Reinforcement Learning

Dong-Ki Kim, Matthew Riemer, Miao Liu, Jakob Nicolaus Foerster, Michael Everett, Chuangchuang Sun, Gerald Tesauro, JONATHAN P HOW

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Curriculum and environment design · 5 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 discounted-return objective (LILI) with the average-reward objective (FURTHER)learning-aware MARL agent · Iterated Bach or Stravinsky vs q-learnerconvergence to optimal equilibrium (B,B)Improved
model other agents' learning (LILI/FURTHER) versus ignoring it (MASAC)MARL agent · Iterated Bach or Stravinsky vs q-learneraverage rewardImproved
increase discount factor gamma toward 1 in LILI (ablation)LILI · Iterated Bach or Stravinsky vs q-learnerconvergence performance and TD errorHurt
FURTHER versus LILI and MASAC in self-playFURTHER · Iterated cooperative game (self-play)average reward / equilibrium reachedImproved
LILI versus MASAC in self-play (modeling others' learning)LILI · Iterated cooperative game (self-play)average rewardImproved
FURTHER versus LILI opponentFURTHER · Iterated matching penniesrelative accumulated rewardImproved
FURTHER versus MASAC opponent compared with versus LILI opponentFURTHER · Iterated matching penniesrelative accumulated rewardImproved
FURTHER versus LILI opponentFURTHER · MuJoCo RoboSumoaveraged winning rate: 60.6Improved
FURTHER versus MASAC opponentFURTHER · MuJoCo RoboSumoaveraged winning rate: 63.9Improved
mean-field FURTHER (FURTHER-MF) versus mean-field LILI (LILI-MF)FURTHER-MF · MAgent Battle 25 vs 25reward over timeImproved
greedy versus GLIE learning of opponent jagent i in IPD · Iterated prisoner's dilemmadependence of average reward on initial q-valuesImproved

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