AI Paper Atlas

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

Learning State Representations from Random Deep Action-conditional Predictions

Zeyu Zheng, Vivek Veeriah, Risto Vuorio, Richard Lewis, Satinder Singh

NeurIPS 2021 · Reinforcement learning › Policy gradient and actor-critic · approach: Off-policy actor-critic with expressive policies · 0 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 random deep action-conditional GVFs as auxiliary tasksA2C · 49 Atari gamesmedian human-normalized scoreImproved
Use random deep action-conditional GVFs as auxiliary tasksA2C · 12 DeepMind Lab environmentsmean capped human-normalized scoreImproved
Train representations solely with rGVF auxiliary tasks, stopping RL gradients to the representationA2C · 49 Atari gamesmedian human-normalized scoreImproved
Train representations solely with rGVF auxiliary tasks, stopping RL gradients to the representationA2C · 12 DeepMind Lab environmentsmean capped human-normalized scoreImproved
Add depth to action-conditional prediction targets (ablation)rGVFs · Breakoutgame scoreImproved
Use deep action-conditional predictions instead of shallow predictions (ablation)rGVFs · Six Atari gamesepisode returnImproved
Add action conditioning to random GVFs (ablation)rGVFs · Six Atari gamesepisode returnImproved
Use deep action-conditional predictions instead of discounted-sum predictions (ablation)rGVFs · Six Atari gamesepisode returnMixed
Increase the number of random features (ablation)Random-GVF representation learning · 7×7 grid worldMSEImproved
Increase action-conditional tree depth to 3 (ablation)Grid-world value-function learning · 7×7 grid worldMSE: MSE of 0 at depth 3Improved
Use random features instead of the hand-crafted touch feature (ablation)Random-GVF representation learning · 7×7 grid worldMSEHurt
Use CURL auxiliary learningA2C · 49 Atari gameshuman-normalized scoreHurt

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