AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Deep Reinforcement and InfoMax Learning

Bogdan Mazoure, Remi Tachet des Combes, Thang Long Doan, Philip Bachman, R Devon Hjelm

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 21 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 DRIML auxiliary DIM objective with adaptive lookaheadC51 · Procgen 16 gamesnormalized score: 1.0 -> 1.9Improved
use fixed lookahead with data augmentation (DRIML-fix) instead of C51C51 · Procgen 16 gamesnormalized score: 1.0 -> 1.48Improved
adaptive lookahead k via non-homogeneous geometric sampling instead of random k (ablation)DRIML · Procgen 16 gamesnormalized score: 0.92 -> 1.9Improved
condition DIM prediction on action (ablation)DRIML · Procgen 16 gamesnormalized score: 0.59 -> 1.9Improved
use DRIML-ada instead of C51 per gameC51 · Procgen individual gamesaverage return: bigfish 1.33 -> 4.45; coinrun 29.7 -> 22.88Mixed
use DRIML-ada instead of CURLCURL · Procgen 16 gamesnormalized score: 0.52 -> 1.9Improved
lookahead k=5 instead of k=1 (ablation)DRIML-noact · Procgen fruitbot, jumper, caveflyeraverage return: fruitbot 0.714 -> 5.425; caveflyer 8.263 -> 5.925Mixed
add DRIML auxiliary loss to C51C51 · Continual Ms. PacMan (changing lethal ghost)average training rewardImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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