AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

From Tokens to Latent States: Leveraging Pre-trained Language Models for Improving Partially Observable Reinforcement Learning

Meiju Li, Ruixiang Sun, Xin Li, Mingzhong Wang

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations · 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
use frozen pre-trained TransformerXL belief module (ELSLLM) instead of PPO without memoryPPO · Minigrid UnlockMSE of estimated state-values: 0.0207 -> 0.0004Improved
use ELSLLM instead of LSTM-PPO memoryLSTM-PPO · Minigrid UnlockMSE of estimated state-values: 0.1686 -> 0.0004Improved
use ELSLLM (actions plus observations, JLP) instead of HELM (visual observations only)HELM · Minigrid UnlockMSE of estimated state-values: 0.0098 -> 0.0004Improved
add JLP and MHN input mapping instead of learnable MLP input layers (ablation)ELSLLM · Minigrid Unlockepisode rewardImproved
add pre-trained TransformerXL weights instead of random initialization (ablation)ELSLLM · Minigrid Unlockepisode rewardImproved
add LSTM memory to PPOPPO · Minigrid (7 tasks)episode rewardMixed
add LSTM memory to PPOPPO · RandomMazeepisode 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