AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Multi-task Batch Reinforcement Learning with Metric Learning

Jiachen Li, Quan Vuong, Shuang Liu, Minghua Liu, Kamil Ciosek, Henrik Christensen, Hao Su

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 10 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
Initialize SAC from the MBML multi-task policy instead of random initializationSAC · HumanoidDir-M unseen taskssample efficiency: 85K vs 350K; 76% improvementImproved
Initialize SAC from the MBML multi-task policy instead of random initializationSAC · five MuJoCo task distributionsconvergence speed: up to 80% improvementImproved
Use transition relabelling and the proposed triplet loss rather than neither component (ablation)MBML · unseen task distributionsaverage episode returnsImproved
Remove transition relabelling while retaining a triplet loss with mined context-set examples (ablation)MBML · unseen task distributionsaverage episode returnsHurt
Remove the triplet loss while retaining relabelled transitions (ablation)MBML · unseen task distributionsaverage episode returnsHurt
Remove both transition relabelling and the triplet loss (ablation)MBML · WalkerParamaverage episode returnsNo clear effect
Use a learned reward function for relabelling instead of the ground-truth reward function (ablation)MBML · UmazeGoal-Maverage episode returnsNo clear effect
Use a reward prediction ensemble for relabelling (ablation)MBML initialization for SAC · unseen task distributionsconvergence 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