AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward

Daejin Jo, Sungwoong Kim, Daniel Wontae Nam, Taehwan Kwon, Seungeun Rho, Jongmin Kim, Donghoon Lee

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Reward shaping for sparse rewards · 2 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
replace AE-LSH hash with VQ-VAE hash in LECO (ablation)LECO · DMLab lasertag_three_opponents_smallmean new-hash rate: 86.8% -> 71.6%Improved
replace AE-LSH hash with VQ-VAE hash in LECO (ablation)LECO · DMLab lasertag_three_opponents_largemean new-hash rate: 68.2% -> 58.6%Improved
add task-specific modulation to VQ-only episodic count (ablation)VQ-only · MiniGrid six taskstasks solvedImproved
use VQ hash instead of heuristic DSC discretization (ablation)episodic count · MiniGrid six taskstasks solvedImproved
use VQ hash instead of AE-LSH in LECO (ablation)LECO · MiniGrid six taskstask performanceImproved
add task-specific modulation to AE-LSH (ablation)AE-LSH · MiniGridtask performanceMixed
remove all intrinsic reward (no-Int) (ablation)IMPALA agent · MiniGrid six taskstasks solvedHurt
naive combination of VQ-VAE and LIRPG (LECO-naive) instead of additive modulation (ablation)LECO · MiniGrid and DMLab taskstask performanceHurt
lambda 0 (episodic count only) or 1.0 (modulation only) (ablation)LECO · MiniGrid KeyCorridor and ObstructedMaze-Fulltask solved: lambda=0 or lambda=1.0 vs lambda=0.5Hurt
lambda 0.25 versus 0.75 weighting (ablation)LECO · MiniGridtask performance: lambda=0.25 > lambda=0.75; best at lambda=0.5Mixed
VQ hash size 3x3x8 (MiniGrid) and 3x2x24 (DMLab) versus other sizes (ablation)LECO · MiniGrid and DMLabtask performance: 3x3x8 and 3x2x24 bestImproved
LECO versus NovelD on Noisy-TV MultiRoomLECO · MiniGrid MultiRoomNoisyTV-N7-S4frames to convergence: 3e7 vs 5e7Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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