AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction

Aviral Kumar, Abhishek Gupta, Sergey Levine

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 41 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
Reweight SAC replay-buffer transitions with DisCorSAC · MT10success rate: 50%Improved
Reweight SAC replay-buffer transitions with DisCorSAC · MT10number of tasks making progress: 7/10 vs 3/10Improved
Reweight transitions using estimated target-value error rather than unweighted replay samplingSAC · Meta-World robotic manipulation taskssuccess rateImproved
Reweight transitions using estimated target-value error rather than unweighted replay samplingSAC · OpenAI Gym benchmarks with stochastic rewardssample efficiencyImproved
Reweight replay-buffer transitions with DisCorDQN · Atari: Pong, Breakout, Asterixlearning speed and performanceImproved
Prioritize transitions by Bellman error instead of using DisCor weightsSAC · Meta-World robotic manipulation tasksperformanceHurt
Use the true value error instead of the estimated error bound Δ (ablation)DisCor · Tabular MDPsvalue errorImproved
Use estimated error bound Δ instead of the true value error (ablation)DisCor · Tabular MDPsperformanceImproved
Prioritize transitions by high Bellman error rather than using DisCor's estimated target-error weighting (ablation)DisCor · Tabular MDPs with sparse rewardsperformanceHurt

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