Methods › Reinforcement Learning › Value Function Estimation › Retrace
Retrace
Introduced by Rémi Munos et al. in Safe and Efficient Off-Policy Reinforcement Learning
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Retrace is an off-policy Q-value estimation algorithm which has guaranteed convergence for a target and behaviour policy (π, β). With off-policy rollout for TD learning, we must use importance sampling for the update:
ΔQⁱᵐᵖ(Sₜ, Aₜ) = γᵗ∏_(1≤τ≤t)(π(A_τ|S_τ))/(β(A_τ|S_τ))δₜ
This product term can lead to high variance, so Retrace modifies ΔQ to have importance weights truncated by no more than a constant c:
ΔQⁱᵐᵖ(Sₜ, Aₜ) = γᵗ∏_(1≤τ≤t)min(c, (π(A_τ|S_τ))/(β(A_τ|S_τ)))δₜ
In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.
From the lookup's note on this name: Nothing resolved to this name, but 3 entries in Syntology's graph carry it; the most cited is the paper “RETRACE: Resilience-Guided Trait-Conditioned Craving Estimation from Wearable Physiology in Opioid Use Disorder” (arXiv:2608.14947, citations not recorded). None of them is well cited, so for any better known sense of the name this is still a gap in coverage; they are listed so you can judge, not as a substitute. For arXiv:2608.14947: ask the lookup about it.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 31 · with a code link: 6 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 31 tagged papers has a Syntology run on record
Page 1 of 1: papers 1 to 31 of 31, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
UI-Evol: Automatic Knowledge Evolving for Computer Use Agents 28 May 2025 · 0 repositories · arXiv:2505.21964
-
Generative Artificial Intelligence: Evolving Technology, Growing Societal Impact, and Opportunities for Information Systems Research 25 Feb 2025 · 0 repositories · arXiv:2503.05770
-
Dynamics of Resource Allocation in O-RANs: An In-depth Exploration of On-Policy and Off-Policy Deep Reinforcement Learning for Real-Time Applications 17 Nov 2024 · 0 repositories · arXiv:2412.01839
-
IDRetracor: Towards Visual Forensics Against Malicious Face Swapping 13 Aug 2024 · 0 repositories · arXiv:2408.06635
-
Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues 12 Apr 2024 · 3 repositories · arXiv:2404.08450
-
Off-policy Distributional Q(λ): Distributional RL without Importance Sampling 8 Feb 2024 · 0 repositories · arXiv:2402.05766
-
Network-thinking to optimize surveillance and control of crop parasites. A review 11 Oct 2023 · 0 repositories · arXiv:2310.07442
-
Distributional Estimation of Data Uncertainty for Surveillance Face Anti-spoofing 18 Sep 2023 · 0 repositories · arXiv:2309.09485
-
PDVN: A Patch-based Dual-view Network for Face Liveness Detection using Light Field Focal Stack 17 Jan 2023 · 0 repositories
-
AcceRL: Policy Acceleration Framework for Deep Reinforcement Learning 28 Nov 2022 · 0 repositories · arXiv:2211.15023
-
Asynchronous Curriculum Experience Replay: A Deep Reinforcement Learning Approach for UAV Autonomous Motion Control in Unknown Dynamic Environments 4 Jul 2022 · 0 repositories · arXiv:2207.01251
-
Safe-FinRL: A Low Bias and Variance Deep Reinforcement Learning Implementation for High-Freq Stock Trading 13 Jun 2022 · 0 repositories · arXiv:2206.05910
-
Bias-inducing geometries: an exactly solvable data model with fairness implications 31 May 2022 · 0 repositories · arXiv:2205.15935
-
Deep Learning with Logical Constraints 1 May 2022 · 0 repositories · arXiv:2205.00523
-
Is Word Error Rate a good evaluation metric for Speech Recognition in Indic Languages? 30 Mar 2022 · 0 repositories · arXiv:2203.16601
-
Marginalized Operators for Off-policy Reinforcement Learning 30 Mar 2022 · 0 repositories · arXiv:2203.16177
-
Improving the Efficiency of Off-Policy Reinforcement Learning by Accounting for Past Decisions 23 Dec 2021 · 0 repositories · arXiv:2112.12281
-
Learning Reward Machines: A Study in Partially Observable Reinforcement Learning 17 Dec 2021 · 0 repositories · arXiv:2112.09477
-
Human Languages with Greater Information Density Increase Communication Speed, but Decrease Conversation Breadth 15 Dec 2021 · 0 repositories · arXiv:2112.08491
-
Dynamics of the market states in the space of correlation matrices with applications to financial markets 12 Jul 2021 · 0 repositories · arXiv:2107.05663
-
A-DeepPixBis: Attentional Angular Margin for Face Anti-Spoofing 1 Mar 2021 · 0 repositories
-
[Re] Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention 6 Dec 2020 · 1 repository
-
Exploiting the potential of deep reinforcement learning for classification tasks in high-dimensional and unstructured data 20 Dec 2019 · 0 repositories · arXiv:1912.09595
-
Learning Reward Machines for Partially Observable Reinforcement Learning 1 Dec 2019 · 1 repository
-
Gap-Increasing Policy Evaluation for Efficient and Noise-Tolerant Reinforcement Learning 18 Jun 2019 · 0 repositories · arXiv:1906.07586
-
Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target 22 Jan 2019 · 1 repository · arXiv:1901.07510
-
Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces 11 Feb 2018 · 0 repositories · arXiv:1802.03753
-
Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations 31 Jan 2018 · 0 repositories · arXiv:1801.10459
-
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 15 Apr 2017 · 0 repositories · arXiv:1704.04651
-
Sample Efficient Actor-Critic with Experience Replay 3 Nov 2016 · 7 repositories · arXiv:1611.01224Syntology 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Safe and Efficient Off-Policy Reinforcement Learning 8 Jun 2016 · 3 repositories · arXiv:1606.02647
Tasks archive 2025-07-28
20 shown of 38 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections