AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance

Mingxuan Jing, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Chao Yang, Bin Fang, Huaping Liu

AAAI 2020 · Reinforcement learning › Imitation learning · approach: Imitation combined with RL · 62 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 expert guidance as soft constraint instead of penalty (reward-shaping) termRLfD with imperfect demonstrations · Physical control benchmarks (Hopper, Walker2d, Ant)exact reward: e.g. 2645.58 vs -68.59 on the 111-dim taskImproved
Soft constraint vs Pre-train baseline (continued guidance during training)RLfD · Hopper, Walker2dreward improvement over training: Hopper +973.42, Walker2d +876.40Improved
Anneal constraint tolerance instead of fixing it (epsilon>0 vs 0) (ablation)Soft constraint RLfD · HalfCheetahrewardImproved
Use too large initial tolerance d0 (e.g. 1) (ablation)Soft constraint RLfD · HalfCheetahrewardHurt
Use too small tolerance d0 with imperfect demonstrations (ablation)Soft constraint RLfD · HalfCheetahfinal rewardHurt
Vary annealing factor epsilon around good values (ablation)Soft constraint RLfD · HalfCheetahrewardNo clear effect
Increase number of demonstration state-action pairs (50 to 5000) (ablation)Soft constraint RLfD vs baselines · HalfCheetahrewardImproved
Raise demonstration quality by mixing in more expert data (ablation)All RLfD methods · HalfCheetahrewardImproved

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