AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Tim G. J. Rudner, Cong Lu, Michael Osborne, Yarin Gal, Yee Whye Teh

NeurIPS 2021 · Reinforcement learning › Imitation learning · approach: Imitation combined with RL · 2 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 GP non-parametric behavioral policy instead of parametric NNKL-regularized RL · MuJoCo tasksreturnImproved
use parametric variance functions instead of GP variance (ablation)N-PPAC · door-binary-v0success rate: 20\% vs nearly 100Hurt
floor the behavioral policy variance (ablation)parametric behavioral policies · door-binary-v0success rateNo clear effect
use a single expert demonstration instead of 15 (ablation)GP behavioral policy · HalfCheetah-v2returnNo clear effect
GP behavioral policy vs parametric, 15,000 data pointsKL-regularized RL · HalfCheetah-v2time per epoch: 12.00s / 46.54sHurt
GP behavioral policy vs parametric, 1,000 data pointsKL-regularized RL · door-binary-v0time per epoch: 19.62s / 23.78sHurt
alternative divergence metrics instead of KL (ablation)N-PPAC · MuJoCo and hand tasksreturnHurt
N-PPAC vs AWAC on door openingN-PPAC · door-binary-v0environment interactions to 90\% success: 4$\times$ fewerImproved

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