AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

When Is Generalizable Reinforcement Learning Tractable?

Dhruv Malik, Yuanzhi Li, Pradeep Kumar Ravikumar

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL · 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
Rely on Weak Proximity, even with SIO, instead of a stronger shared-policy conditionAverage Performance generalization · Average Performancequery cost: Ω \left( \min \left \{ \vert \ActSet \vert^H, 2^d \right\} \right)Hurt
Rely on Weak Proximity, even with SIO, instead of a stronger shared-policy conditionMeta RL generalization · Meta RLtraining query cost: Ω \left( \min \left \{ \vert \ActSet \vert^H, 2^d \right\} \right)Hurt
Allow transition variation Θ(1/H) while keeping rewards shared under Weak Proximity and SIOAverage Performance generalization · Average Performancequery cost: Ω \left( \min \left \{ \vert \ActSet \vert^H, 2^d \right\} \right)Hurt
Allow transition variation Θ(1/H) while keeping rewards shared under Weak Proximity and SIOMeta RL generalization · Meta RLtraining query cost: Ω \left( \min \left \{ \vert \ActSet \vert^H, 2^d \right\} \right)Hurt
Use Strong Proximity with a policy near-optimal from every state, shared deterministic transitions, and WIOGenRL · Average Performanceexpected value suboptimality: \epsilon + 3 \polsub H + 3 \solvesub HImproved
Keep both reward and transition variation o(1/H)Generalization under the Simulation Lemma · Average Performance and Meta RLvalue suboptimality: o(1)Improved

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