AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Large Language Models can Implement Policy Iteration

Ethan Brooks, Logan A Walls, Richard Lewis, Satinder Singh

NeurIPS 2023 · Reinforcement learning › Imitation learning · approach: Imitation combined with RL · 6 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 LLM-rollout Q-values with argmax policy improvement instead of the No argmax imitation baselineICPI · six illustrative domainsnormalized regretImproved
ICPI instead of tabular Q-learningICPI · six illustrative domainsnormalized regretImproved
ICPI instead of nearest-neighbor trajectory matching modelICPI · six illustrative domainsnormalized regretImproved
remove hints from the prompt format (ablation)ICPI · six illustrative domainsnormalized regretMixed
remove balancing of terminal and reward time-steps in prompts (ablation)ICPI · six illustrative domainsnormalized regretMixed
remove constraints on prompt time-steps (ablation)ICPI · six illustrative domainsnormalized regretMixed
double recency cutoff from 8 to 16 trajectories (ablation)ICPI · six illustrative domainsnormalized regretMixed
replace Codex with smaller models GPT-J, InCoder, OPT-30B, code-cushman-001ICPI · six illustrative domainsnormalized regretHurt

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