AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay

Haiyan Yin, Sinno Pan

AAAI 2017 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 119 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
proposed multi-task distillation architecture vs DISTmulti-task policy distillation · Atari 10 games% of teacher score (geometric mean): 92.41 -> 103.8Improved
proposed multi-task distillation architecture vs AMNmulti-task policy distillation · Atari 10 games% of teacher score (geometric mean): 93.5 -> 103.8Improved
proposed architecture vs DIST/AMNmulti-task policy distillation · Atari 10 gamessteps to converge: 1.5M vs at least 2.5M stepsImproved
use hierarchical prioritized replay instead of uniform sampling (ablation)proposed architecture · Breakout, Q*bertsteps to reach target score: approximately 50% of the stepsImproved
use hierarchical prioritized replay instead of uniform sampling (ablation)proposed architecture · Freeway, PongscoreNo clear effect
vary partition size p (5, 10, 15) (ablation)H-PR · Atari multi-tasklearning speedNo clear effect

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