mlsanityData to 7 Oct 2026

Selective Credit Assignment

arXiv 2202.09699 ↗First posted 20 Feb 2022cs.LG cs.AI stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Efficient credit assignment is essential for reinforcement learning algorithms in both prediction and control settings. We describe a unified view on temporal-difference algorithms for selective credit assignment. These selective algorithms apply weightings to quantify the contribution of learning updates. We present insights into applying weightings to value-based learning and planning algorithms, and describe their role in mediating the backward credit distribution in prediction and control. Within this space, we identify some existing online learning algorithms that can assign credit selectively as special cases, as well as add new algorithms that assign credit backward in time counterfactually, allowing credit to be assigned off-trajectory and off-policy.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 53 references that are in the map. First posted on arXiv 20 Feb 2022.

Builds on

23 of 53 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016The Option-Critic Architecturecited by 433
  3. 2018Deep Reinforcement Learning and the Deadly Triadcited by 170
  4. 2018RUDDER: Return Decomposition for Delayed Rewardscited by 162
  5. 2018Meta-Gradient Reinforcement Learningcited by 156
  6. 2019When to use parametric models in reinforcement learning?cited by 118
  7. 2015An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learningcited by 103
  8. 2019Hindsight Credit Assignmentcited by 74
  9. 2020DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correctioncited by 71
  10. 2020Counterfactual Credit Assignment in Model-Free Reinforcement Learningcited by 60
  11. 2018Optimizing Agent Behavior over Long Time Scales by Transporting Valuecited by 57
  12. 2016Unifying task specification in reinforcement learningcited by 41
11 more
  1. 2018Sparse Attentive Backtracking: Temporal CreditAssignment Through Remindingcited by 33
  2. 2020Expected Eligibility Tracescited by 27
  3. 2019The Termination Criticcited by 24
  4. 2019On Inductive Biases in Deep Reinforcement Learningcited by 22
  5. 2016A Greedy Approach to Adapting the Trace Parameter for Temporal Difference Learningcited by 20
  6. 2015Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysiscited by 17
  7. 2020Forethought and Hindsight in Credit Assignmentcited by 16
  8. 2020Learning Retrospective Knowledge with Reverse Reinforcement Learningcited by 8
  9. 2021Preferential Temporal Difference Learningcited by 6
  10. 2015Learning to Predict Independent of Spancited by 5
  11. 2021Learning Expected Emphatic Traces for Deep RLcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 0; 2026: 1.

4 papers.

  1. 2023A Survey of Temporal Credit Assignment in Deep Reinforcement Learningcited by 56
  2. 2023Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learningcited by 4
  3. 2026Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVRcited by 4
  4. 2023Discerning Temporal Difference Learningcited by 0