AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Guided Policy Optimization under Partial Observability

Yueheng Li, Guangming Xie, Zongqing Lu

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 4 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 RL auxiliary loss to learner supervision (GPO-penalty/clip vs GPO-naive) (ablation)GPO · Brax POMDP tasksnormalized returnImproved
constrain the guider to the learner's imitable region (GPO-naive vs PPO+BC) (ablation)GPO · Brax POMDP tasksnormalized returnImproved
collect data with the guider as behavior policy (GPO-ablation vs PPO-asym) (ablation)PPO with asymmetric value · Brax Humanoidnormalized returnImproved
use a larger KL threshold in GPO-penalty (ablation)GPO-penalty · POPGym CountRecallEasy and BattleshipEasyreturnImproved
use a larger KL threshold in GPO-penalty (ablation)GPO-penalty · POPGym CountRecallHard and BattleshipMediumreturnHurt
add a pre-trained privileged teacher with ADVISOR or PPO+BCPPO · partially observable AntreturnNo clear effect
add asymmetric value function input to PPOPPO · POPGym memory tasksreturnMixed

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