AI Paper Atlas

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

Bootstrap Estimated Uncertainty of the Environment Model for Model-Based Reinforcement Learning

Wenzhen Huang, Junge Zhang, Kaiqi Huang

AAAI 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 16 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 per-depth bootstrapped environment modules with priorTreeQN-2 · Atari (9 games)best mean score: Amidar 1170 -> 2059; Q*Bert 15970 -> 27285Improved
add bootstrapped modulesTreeQN-2 · Atari Seaquestbest mean score: 8241 -> 6415Hurt
bootstrap modules per depth rather than the entire TreeQN (ablation)Bootstrapped TreeQN · Atari (9 games)best mean score: Seaquest 4610 -> 6415; Amidar 1188 -> 2059Improved
sample target values from bootstrap distribution instead of fixed target modules (ablation)Bootstrapped TreeQN · Atari (9 games)best mean score: Frostbite 4279 vs 2889 is reversed; Krull 9590 -> 12010; Amidar 1527 -> 2059Improved
add frozen random prior network (ablation)Bootstrapped TreeQN · Atari (9 games)best mean score: Amidar 1888 -> 2059; Frostbite 6039 vs 2889; Seaquest 7313 vs 6415Mixed
use bootstrapped modulesTreeQN · Box Pushingreward prediction lossImproved
use bootstrapped modulesTreeQN · Box Pushingaverage rewardNo clear effect
double embedding size of TreeQN (wide) instead of adding bootstrapTreeQN-2 · Atari (9 games)best mean score: Alien 2497 -> 2709; Seaquest 8241 -> 8956Mixed

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