AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Parametrized Quantum Policies for Reinforcement Learning

Sofiene Jerbi, Casper Gyurik, Simon Callum Marshall, Hans J Briegel, Vedran Dunjko

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: RL with tree search for discovery · 10 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 softmax-PQC policy (softmax over trainable-observable expectations) instead of raw-PQC (ablation)PQC policy · CartPole, MountainCar, Acrobotlearning performanceImproved
increase PQC depth (up to D_enc=10) (ablation)softmax-PQC · CartPole, MountainCar, Acrobotlearning performanceImproved
train input-scaling parameters lambda instead of fixing them to 1 (ablation)softmax-PQC · CartPole, MountainCar, Acrobotlearning performanceImproved
train observable weights instead of fixing them to 1 (trainable greediness) (ablation)softmax-PQC · CartPole, MountainCar, Acrobotperformance and convergence speedImproved
fix a high inverse temperature beta (large observable norm) (ablation)softmax-PQC · benchmark environmentslearning performanceHurt
increase depth and train scaling parameters (ablation)raw-PQC · benchmark environmentslearning performanceImproved
use softmax-PQC instead of ReLU DNN (depth 4, width 16)policy class · PQC-generated SL and cliffwalk environmentslearning performanceImproved
add cliffwalk temporal structure to the environmentPQC vs DNN gap · PQC-generated environmentsperformance separationImproved

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