AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process

Jiayu Chen, Vaneet Aggarwal, Tian Lan

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Unsupervised skill discovery · 1 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 only the landmark-based mutual information term instead of DIAYN, VIC or VALOR objectives (ablation)ODPP (L^IB only) · Point Room trajectoriesqualitative diversity and coverageImproved
add DPP coverage term L1 (ablation)ODPP (L^IB) · Point Room trajectoriesqualitative diversity and coverageImproved
add DPP consistency and diversity terms L2 and L3 (ablation)ODPP (L^IB, L1) · Point Room trajectoriesqualitative diversity and coverageImproved
define trajectory features with Structured DPP instead of decoder hidden layer output (ablation)ODPP · Point Room trajectoriesqualitative diversity and coverageImproved
set feature dimension D=2 so ODPP mimics Laplacian-based DCO (ablation)ODPP · Point Corridorqualitative diversity and coverageNo clear effect
use normal setting D=30 with 10 options instead of D=2 (ablation)ODPP · Point Corridorqualitative diversity and coverageImproved
use ODPP options with a learned option selector instead of PPO on raw actionsBase RL (PPO) · Point Room/Corridor goal-achievingmean returnImproved
use ODPP options to initialize policy for exploration instead of baselinesVIC, DIAYN, VALOR, DCO · Ant Room/Corridor explorationtrajectory returnImproved
initialize option selector with the learned prior network (ablation)option selector · downstream taskdownstream returnImproved
increase number of simultaneously learned options to 10, 20, 40, 60 (ablation)ODPP · Ant locomotiontrajectory reward mean and stdNo clear effect
compare ODPP skills against DIAYN, VIC, VALOR, DADS and APSODPP · CartPole, AirRaid, RiverRaidaverage cumulative rewardImproved

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