AI Paper Atlas

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

Harnessing Structures for Value-Based Planning and Reinforcement Learning

Yuzhe Yang, Guo Zhang, Zhi Xu, Dina Katabi

ICLR 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting theory · 15 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 SVP with 20% observation probability instead of the optimal policyInverted Pendulum, 400×100 discretization · Inverted Pendulumaverage deviation (degree): 1.49 -> 2.07Hurt
Use SVP with 20% observation probability instead of the optimal policyInverted Pendulum, 2500×1000 discretization · Inverted Pendulumaverage deviation (degree): 0.53 -> 1.92Hurt
Use SVP with 20% observation probability instead of the optimal policyInverted Pendulum, 10000×4000 discretization · Inverted Pendulumaverage deviation (degree): 0.18 -> 0.96Hurt
Apply SV-RL to low-rank Atari games rather than the vanilla value-based algorithmDQN, double DQN, and dueling DQN · Low-rank Atari gamesmean rewardImproved
Apply SV-RL to higher-rank gamesValue-based Atari methods · High-rank Atari games, including Seaquestmean rewardMixed
Increase SV-RL batch size from 32 to 128 (ablation)DQN · SeaquestperformanceImproved
Use a smaller batch size (ablation)SV-RL · SeaquestperformanceHurt

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