AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL

Charles Packer, Pieter Abbeel, Joseph E. Gonzalez

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Task-inference meta-RL · 3 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 hindsight task relabeling during sparse-reward meta-trainingPEARL · Sparse-reward goal-reaching environmentsaverage sparse returnImproved
Use sparse-reward HTR meta-training instead of dense-reward trainingPEARL · Sparse-reward goal-reaching environmentsaverage sparse returnNo clear effect
Add HTR to PEARL rather than use unmodified sparse-reward PEARLPEARL · Held-out sparse-reward tasksaverage sparse returnImproved
Use Episode Clustering instead of Single Episode Relabeling (ablation)HTR · Point Robotaverage returnNo clear effect
Set relabeling probability K to 0.1 or 0.3 rather than higher tested probabilities (ablation)HTR · Point Robotaverage returnImproved
Increase relabeling probability K to 0.5 or 0.8 (ablation)HTR · Point Robotmean relabelled task distance: 2.0 -> 0.5Hurt
Sample context and RL batches from the same relabelled episode (ablation)HTR with SER · Sparse-reward meta-RLreward in the RL batchImproved

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