AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Policy Continuation with Hindsight Inverse Dynamics

Hao Sun, Zhizhong Li, Xiaotong Liu, Bolei Zhou, Dahua Lin

NeurIPS 2019 · Reinforcement learning › Visual and representation RL · approach: Goal-conditioned policy learning · 6 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 PEHID instead of DDPG + HERDDPG + HER baseline · FetchPushsuccess rate: 1.00 -> 0.95Hurt
Use PEHID instead of DDPG + HERDDPG + HER baseline · FetchSlidesuccess rate: 0.30 -> 0.38Improved
Use PEHID instead of DDPG + HERDDPG + HER baseline · FetchPickAndPlacesuccess rate: 0.60 -> 0.75Improved
Use PCHID with PPOPPO · FetchReachsuccess rateNo clear effect
Add HER to PCHIDPCHID · FetchReachsuccess rateImproved
Use 5-step HID with HER instead of 1-step HIDPCHID on GridWorld · GridWorldrollout success rateImproved
Augment DQN with HERDQN · GridWorldrollout success rateImproved
Use joint training rather than output averaging or intrinsic rewardPCHID combined with other RL algorithms · GridWorld and FetchReachperformanceImproved

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