AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Neural Episodic Control with State Abstraction

Zhuo Li, Derui Zhu, Yujing Hu, Xiaofei Xie, Lei Ma, YAN ZHENG, Yan Song, Yingfeng Chen, Jianjun Zhao

ICLR 2023 · Reinforcement learning › Visual and representation RL · approach: Latent-space world models · 5 citations (OpenAlex)

Read the paper

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 three-step rather than one-step or two-step abstract patterns (ablation)NECSA · Walker2d-v3 and Hopper-v3sample efficiencyImproved
use longer patterns beyond three steps (ablation)NECSA · MuJoCo taskssample efficiencyHurt
measure patterns with reward confidence scores instead of Q-values (ablation)NECSA · MuJoCo evaluationsample efficiencyImproved
abstract state-action pairs instead of states alone (ablation)NECSA · MuJoCo tasksperformanceImproved
abstract policy hidden outputs instead of raw image states (ablation)NECSA · Atari gamesperformanceImproved
increase grid granularity (ablation)NECSA · Walker2d-v3, Hopper-v3, and AlienperformanceMixed
set reward-shaping magnitude epsilon within the reported best range (ablation)NECSA · Walker2d-v3 and Hopper-v3performanceImproved
set epsilon greater or smaller than the reported best range (ablation)NECSA · Walker2d-v3 and Hopper-v3performanceHurt
add NECSA to the backbone reinforcement-learning algorithm (ablation)TD3 and DDPG · Walker2d-v3 and Hopper-v3sample efficiencyImproved
add NECSA to DrQ-v2 (ablation)DrQ-v2 · DMControl Walker-Walk and Hopper-Standsample efficiencyImproved
add NECSA to DrQ-v2 (ablation)DrQ-v2 · DMControl Cartpole-BalanceperformanceNo clear effect
use Gaussian random projection to reduce state or hidden-output dimensions (ablation)NECSA · high-dimensional MuJoCo and image-state tasksperformanceNo clear effect

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