AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning Retrospective Knowledge with Reverse Reinforcement Learning

Shangtong Zhang, Vivek Veeriah, Shimon Whiteson

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL · 3 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 Reverse GVF auxiliary tasks to IMPALAIMPALA · 10 Atari gamesgame performance: 7 out of 10 games; improvement is larger than 25% in 5 gamesImproved
Use Reverse GVF instead of reward prediction as the auxiliary taskIMPALA · 10 Atari gamesgame performance: all 10 tested gamesImproved
Use Reverse GVF instead of pixel control as the auxiliary taskIMPALA · 10 Atari gamesgame performance: 8 out of 10 tested gamesMixed
Use Reverse GVF rather than predictive GVF auxiliary tasksIMPALA · 10 Atari gamesgame performance: 3 gamesMixed
Use smaller λ in Reverse TD(λ) (ablation)Reverse TD(λ) · Microdronemean value errorImproved
Use a single observed reverse return and its state-conditioned learned distribution for anomaly detectionDistributional Reverse GVF · Microdrone anomaly detectionanomaly probabilityImproved
Use a single observed reverse return and its state-conditioned learned distribution for anomaly detectionDistributional Reverse GVF · Reacher anomaly detectionprobability of anomaly: higher than 0.8Mixed

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