AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Curriculum-Based Asymmetric Multi-Task Reinforcement Learning

Hanchi Huang, Deheng Ye, Li Shen, Wei Liu

TPAMI 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 29 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
add mode switching and multiple ranking functions (vs AMRL) (ablation)CAMRL · MT10 ablation (avg of 10 tasks)avg reward: 1844.9 -> 5638.7Improved
add mode switching (ablation)CAMRL · MT10 ablation (avg of 10 tasks)avg reward: 2779.5 -> 5638.7Improved
use finite a in indicator (vs a=positive infinity) (ablation)CAMRL · MT10 ablation (avg of 10 tasks)avg reward: 4571.3 -> 5638.7Improved
use finite b in indicator (vs b=positive infinity) (ablation)CAMRL · MT10 ablation (avg of 10 tasks)avg reward: 4465.1 -> 5638.7Improved
use nonzero c (vs c=0) (ablation)CAMRL · MT10 ablation (avg of 10 tasks)avg reward: 4929.1 -> 5638.7Improved
use nonzero d in tanh ranking (vs d=0) (ablation)CAMRL · MT10 ablation (avg of 10 tasks)avg reward: 3255.7 -> 5638.7Improved
use nonzero lambda2 (vs 0) (ablation)CAMRL · MT10 ablation (avg of 10 tasks)avg reward: 4525.4 -> 5638.7Improved
use nonzero lambda3 (vs 0) (ablation)CAMRL · MT10 ablation (avg of 10 tasks)avg reward: 5386.8 -> 5638.7Improved
use nonzero lambda4 (vs 0) (ablation)CAMRL · MT10 ablation (avg of 10 tasks)avg reward: 5528.7 -> 5638.7Improved
add prior-knowledge differentiable ranking lossCAMRL · MT10reward: better on 5 of 10 tasksMixed
add prior-knowledge differentiable ranking lossCAMRL · MT50reward: better on 38 of 50 tasksImproved
add prior-knowledge differentiable ranking lossCAMRL · Atarireward: better on 8 of 10 tasksImproved

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