AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling

Rohan Chitnis, Tom Silver, Joshua B. Tenenbaum, Leslie Pack Kaelbling, Tomás Lozano-Pérez

AAAI 2021 · Reinforcement learning › Visual and representation RL · approach: Goal-conditioned policy learning · 13 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 GLIB for exploration instead of prior exploration methodsRelational model-based RL · Blocks, Gripper, Keys and Doors, Exploding Blocks, Triangle Tireworld, PyBulletplanning success rateImproved
Use GLIB for exploration instead of prior exploration methodsRelational model-based RL · Six evaluated domainsprediction errorImproved
Use lifted goals rather than ground goalsGLIB · All domains except Triangle Tireworldplanning success rateImproved
Use ground goals rather than lifted goalsGLIB · Triangle Tireworldplanning success rateImproved
Use novelty-based goal sampling rather than repeatedly sampling goals without novelty filtering (ablation)GLIB · Relational model explorationoverall performanceImproved
Filter out static and mutex goals (ablation)GLIB · All evaluated domainsruntimeImproved
Filter out static and mutex goals (ablation)GLIB · All evaluated domainsplanning success rateNo clear effect
Set the lifted-goal literal bound to k=2 rather than k=1 (ablation)GLIB lifted · Evaluated domainsplanning performanceImproved
Use lifted rather than ground novelty in a domain with few predicates (ablation)GLIB · Triangle Tireworldplanning success rateHurt
Plan toward babbled goals using the current learned modelGLIB · Keys and Doorssample efficiencyImproved

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