AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Large Language Models Are Semi-Parametric Reinforcement Learning Agents

Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, Kai Yu

NeurIPS 2023 · Multi-agent systems and games › LLM agents · approach: Self-evolving language agent learning · 10 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 n-step bootstrapping to Q updates (ablation)Rememberer · WikiHowsuccess rate: 0.89 -> 0.93Improved
add n-step bootstrapping to Q updates (ablation)Rememberer · WebShopsuccess rate: 0.36 -> 0.37No clear effect
add n-step bootstrapping to Q updates (ablation)Rememberer · WebShopabs error of reward estimation: 0.22 -> 0.02Improved
add random advice when no suitable candidates (ablation)Rememberer · WikiHowsuccess rate: 0.90 -> 0.93Improved
add random advice when no suitable candidates (ablation)Rememberer · WebShopsuccess rate: 0.37 -> 0.37No clear effect
include discouraged actions in action advice (ablation)Rememberer · WikiHowsuccess rate: 0.81 -> 0.93Improved
add task similarity f_g to retrieval (ablation)Rememberer · WikiHowsuccess rate: 0.94 -> 0.93No clear effect
add observation similarity f_o to retrieval (ablation)Rememberer · WikiHowsuccess rate: 0.87 -> 0.93Improved
use Double Q-Learning instead of plain Q-LearningRememberer · WikiHowabs error of reward estimation: 0.12 -> 0.43Hurt
add experience memory with RL updates (Rememberer vs fixed exemplars)text-davinci-003 agent · WebShopsuccess rate: 0.29 -> 0.39Improved

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