Methods › Reinforcement Learning › On-Policy TD Control › TD Lambda

TD Lambda

14 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

TD_INLINE_MATH_1 is a generalisation of TD_INLINE_MATH_2 reinforcement learning algorithms, but it employs an eligibility trace λ and λ-weighted returns. The eligibility trace vector is initialized to zero at the beginning of the episode, and it is incremented on each time step by the value gradient, and then fades away by γλ:

z₋₁ = 0 zₜ = γλzₜ₋₁ + ∇v̂(Sₜ, 𝐰ₜ), 0 ≤t ≤T

The eligibility trace keeps track of which components of the weight vector contribute to recent state valuations. Here ∇v̂(Sₜ, 𝐰ₜ) is the feature vector.

The TD error for state-value prediction is:

δₜ = Rₜ₊₁ + γv̂Sₜ₊₁, 𝐰ₜ) - v̂(Sₜ, 𝐰ₜ)

In TD_INLINE_MATH_1, the weight vector is updated on each step proportional to the scalar TD error and the vector eligibility trace:

𝐰ₜ₊₁ = 𝐰ₜ + αδ𝐳ₜ

Source: Sutton and Barto, Reinforcement Learning, 2nd Edition

Papers archive 2025-07-28

14 shown of 14, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

17 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Starcraft II7
Starcraft6
Reinforcement Learning (RL)5
Reinforcement Learning4
reinforcement-learning4
Decision Making2
AI Agent1
CPU1
Deep Reinforcement Learning1
Diversity1
Hierarchical Reinforcement Learning1
Imitation Learning1
Language Modelling1
Large Language Model1
Model Predictive Control1
Offline RL1
Transfer Learning1

Usage over time archive 2025-07-28

Papers per year tagged with TD Lambda: 2016 to 2025, peak 5 5 0 2016: 1 paper 2016 2017: 0 papers 2017 2018: 0 papers 2018 2019: 1 paper 2019 2020: 1 paper 2020 2021: 5 papers 2021 2022: 1 paper 2022 2023: 3 papers 2023 2024: 1 paper 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (14 dated). Bars are counts, not a trend claim.

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

On-Policy TD Control

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