Methods › Reinforcement Learning › On-Policy TD Control › Sarsa
Sarsa
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Sarsa is an on-policy TD control algorithm:
Q(Sₜ, Aₜ) ←Q(Sₜ, Aₜ) + α[Rₜ₊₁ + γQ(Sₜ₊₁, Aₜ₊₁) - Q(Sₜ, Aₜ)]
This update is done after every transition from a nonterminal state Sₜ. if Sₜ₊₁ is terminal, then Q(Sₜ₊₁, Aₜ₊₁) is defined as zero.
To design an on-policy control algorithm using Sarsa, we estimate q_π for a behaviour policy π and then change π towards greediness with respect to q_π.
Source: Sutton and Barto, Reinforcement Learning, 2nd Edition
Papers archive 2025-07-28
30 shown of 56, 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.
-
A Unified Anti-Jamming Design in Complex Environments Based on Cross-Modal Fusion and Intelligent Decision-Making 9 Jun 2025 · 0 repositories · arXiv:2506.07532
-
Reinforcement Learning for Hanabi 31 May 2025 · 0 repositories · arXiv:2506.00458
-
Convergent NMPC-based Reinforcement Learning Using Deep Expected Sarsa and Nonlinear Temporal Difference Learning 7 Feb 2025 · 0 repositories · arXiv:2502.04925
-
Segmenting Action-Value Functions Over Time-Scales in SARSA via TD(Δ) 22 Nov 2024 · 0 repositories · arXiv:2411.14783
-
A novel agent with formal goal-reaching guarantees: an experimental study with a mobile robot 23 Sep 2024 · 0 repositories · arXiv:2409.14867
-
Reinforcement Learning for Rate Maximization in IRS-aided OWC Networks 7 Sep 2024 · 0 repositories · arXiv:2409.04842
-
Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach 23 Aug 2024 · 0 repositories · arXiv:2408.13139
-
The State-Action-Reward-State-Action Algorithm in Spatial Prisoner's Dilemma Game 25 Jun 2024 · 0 repositories · arXiv:2406.17326
-
SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems 7 May 2024 · 1 repository · arXiv:2405.03967
-
Research on Robot Path Planning Based on Reinforcement Learning 22 Apr 2024 · 1 repository · arXiv:2404.14077
-
State-Separated SARSA: A Practical Sequential Decision-Making Algorithm with Recovering Rewards 18 Mar 2024 · 0 repositories · arXiv:2403.11520
-
Enhancing Classification Performance via Reinforcement Learning for Feature Selection 9 Mar 2024 · 0 repositories · arXiv:2403.05979
-
An Index Policy Based on Sarsa and Q-learning for Heterogeneous Smart Target Tracking 19 Feb 2024 · 0 repositories · arXiv:2402.12015
-
Using Reinforcement Learning to Optimize Responses in Care Processes: A Case Study on Aggression Incidents 2 Oct 2023 · 0 repositories · arXiv:2310.00981
-
Career Path Recommendations for Long-term Income Maximization: A Reinforcement Learning Approach 11 Sep 2023 · 0 repositories · arXiv:2309.05391
-
Exploring reinforcement learning techniques for discrete and continuous control tasks in the MuJoCo environment 20 Jul 2023 · 1 repository · arXiv:2307.11166
-
PCG-based Static Underground Garage Scenario Generation 8 Jul 2023 · 0 repositories · arXiv:2307.03988
-
Convergence of SARSA with linear function approximation: The random horizon case 7 Jun 2023 · 0 repositories · arXiv:2306.04548
-
On Modeling Network Slicing Communication Resources with SARSA Optimization 11 Jan 2023 · 0 repositories · arXiv:2301.04696
-
Analysis of Reinforcement Learning Schemes for Trajectory Optimization of an Aerial Radio Unit 18 Nov 2022 · 0 repositories · arXiv:2211.10524
-
SlateFree: a Model-Free Decomposition for Reinforcement Learning with Slate Actions 5 Sep 2022 · 0 repositories · arXiv:2209.01876
-
Solving Royal Game of Ur Using Reinforcement Learning 23 Aug 2022 · 2 repositories · arXiv:2208.10669
-
On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios 19 Jul 2022 · 0 repositories · arXiv:2207.09372
-
Reinforced Lin-Kernighan-Helsgaun Algorithms for the Traveling Salesman Problems 8 Jul 2022 · 1 repository · arXiv:2207.03876
-
Does DQN Learn? 26 May 2022 · 0 repositories · arXiv:2205.13617
-
On the Convergence of SARSA with Linear Function Approximation 14 Feb 2022 · 0 repositories · arXiv:2202.06828
-
A study of first-passage time minimization via Q-learning in heated gridworlds 5 Oct 2021 · 0 repositories · arXiv:2110.02129
-
Enhancing Video Analytics Accuracy via Real-time Automated Camera Parameter Tuning 8 Jul 2021 · 0 repositories · arXiv:2107.03964
-
Reinforcement Learning for Physical Layer Communications 22 Jun 2021 · 1 repository · arXiv:2106.11595
-
A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes 3 Jun 2021 · 0 repositories · arXiv:2106.01577
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