AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience

Beomjoon Kim, Leslie Pack Kaelbling, Tomás Lozano-Pérez

AAAI 2019 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 19 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
guide planner with ADMON-learned policy instead of uniform samplingsampling-based G-TAMP planner · Conveyor belt domainplanning time to 95% optimal: 1200+ s -> 400 sImproved
guide planner with ADMON-learned policy instead of uniform samplingsampling-based G-TAMP planner · Object fetch domainplanning time to clear optimal objects: 3500 s -> 1500 sImproved
ADMON (reward + imitation of planning data) vs PPO/DDPGpolicy learning · Conveyor belt domainreward learning curve vs data sizeImproved
ADMON vs GAIL (treating planning data as optimal demos)policy learning · Conveyor belt domainreward learning curveImproved
ADMON vs GAILpolicy learning · Object fetch domainreward learning curveImproved
ADMON vs DDPGpolicy learning · Object fetch domainreward learning curveImproved
ADMON vs DDPG in planningpolicy-guided planner · Object fetch domainobjects cleared over timeImproved
PPO vs ADMON in object fetch with more transitionsPPO · Object fetch domainreward learning curveMixed

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