AI Paper Atlas

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

A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents

YAN ZHENG, Zhaopeng Meng, Jianye Hao, Zongzhang Zhang, Tianpei Yang, Changjie Fan

NeurIPS 2018 · Multi-agent systems and games › Games and equilibria · approach: Learning in Markov games · 52 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
add rectified belief model (opponent-model-based) to BPR+ detection (ablation)BPR+ · gridworld, navigation, soccer gamesopponent policy detection accuracyImproved
opponent switches policy more frequentlyBPR+ vs deep BPR+(D) · three gamesdetection accuracyMixed
add distilled policy network for initializing learning against unknown opponent policies (ablation)deep BPR+ · three games with unknown policiesnormalized cumulative rewardImproved
use rectified belief model with or without DPN (ablation)BPR+ · three gamescumulative rewardImproved
initialize from DPN shared conv layers instead of individual learned response policies (ablation)online DQN learning · navigation game, unknown policies A and Elearning performance and stabilityImproved
initialize from an individual poorly chosen response policy (ablation)online DQN learning · navigation gameonline learning performanceHurt
BPR without learning new policies vs BPR+/deep BPR+BPR · three games with unknown policiescumulative rewardHurt

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