AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Few-Shot Bayesian Imitation Learning with Logical Program Policies

Tom Silver, Kelsey R. Allen, Alex K. Lew, Leslie Pack Kaelbling, Josh Tenenbaum

AAAI 2020 · Reinforcement learning › Imitation learning · approach: Offline imitation from imperfect data · 32 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 the LPP structured policy class and Bayesian learning from one demonstrationBreakoutNoFrameskip-v4 · 10 held-out instances, 500 framesreward: reward of 3 in all 10 casesImproved
Use the LPP structured policy class and Bayesian learning from at most five demonstrationsNim and Checkmate Tactic · held-out task instancesdemonstrations needed for test performance 1.0: 20 -- 1,000x data efficiency gainsImproved
Search complete policies by vanilla program induction instead of learning Boolean combinations incrementallyVPI · all tasks other than Nimtest performanceHurt
Replace Boolean learning with a neural network classifier over enumerated DSL features (ablation)LPP · six strategy gamestest performanceHurt
Use an L1-regularized neural network classifier over enumerated DSL features (ablation)LPP · six strategy gamestest performanceHurt
Replace the grammatical prior with a uniform prior (ablation)LPP · six strategy gamestest performanceHurt
Replace the grammatical prior with a prior penalizing only the number of top-level programs (ablation)LPP · six strategy gamestest performanceHurt
Assume no demonstration noise in the likelihoodLPP · Nim with noisy demonstrationstest performanceHurt
Use too high a noise probability in the likelihoodLPP · Nimtest performanceHurt
Use a very small but nonzero noise probability in the likelihoodLPP · Nim with noisy demonstrationstest performanceImproved

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