mlsanityData to 7 Oct 2026

Reinforcement Learning with Segment Feedback

arXiv 2502.01876 ↗First posted 3 Feb 2025cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Standard reinforcement learning (RL) assumes that an agent can observe a reward for each state-action pair. However, in practical applications, it is often difficult and costly to collect a reward for each state-action pair. While there have been several works considering RL with trajectory feedback, it is unclear if trajectory feedback is inefficient for learning when trajectories are long. In this work, we consider a model named RL with segment feedback, which offers a general paradigm filling the gap between per-state-action feedback and trajectory feedback. In this model, we consider an episodic Markov decision process (MDP), where each episode is divided into m segments, and the agent observes reward feedback only at the end of each segment. Under this model, we study two popular feedback settings: binary feedback and sum feedback, where the agent observes a binary outcome and a reward sum according to the underlying reward function, respectively. To investigate the impact of the number of segments m on learning performance, we design efficient algorithms and establish regret upper and lower bounds for both feedback settings. Our theoretical and experimental results show that: under binary feedback, increasing the number of segments m decreases the regret at an exponential rate; in contrast, surprisingly, under sum feedback, increasing m does not reduce the regret significantly.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 12 of its 24 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

12 of 24 references.

References · 12

  1. 2017Minimax Regret Bounds for Reinforcement Learningcited by 500
  2. 2018Is Q-learning Provably Efficient?cited by 485
  3. 2015An Introduction to Matrix Concentration Inequalitiescited by 391
  4. 2019Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Boundscited by 194
  5. 2017Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learningcited by 175
  6. 2020Improved Optimistic Algorithms for Logistic Banditscited by 117
  7. 2020Fast active learning for pure exploration in reinforcement learningcited by 92
  8. 2020Reinforcement Learning with Trajectory Feedbackcited by 40
  9. 2021On the Theory of Reinforcement Learning with Once-per-Episode Feedbackcited by 32
  10. 2020Self-Concordant Analysis of Generalized Linear Bandits with Forgettingcited by 29
  11. 2017Near-Optimal Discrete Optimization for Experimental Design: A Regret Minimization Approachcited by 19
  12. 2024Harnessing Causality in Reinforcement Learning With Bagged Decision Timescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Temporal GRPO: Beyond Trajectory-Level Credit in Vision-Language-Action Reinforcement Learningcited by 1
  2. 2026Learning Markov Decision Processes under Fully Bandit Feedbackcited by 0
  3. 2026SP3O: Reinforcement Learning from Segment Preferences without Reward Modelingcited by 0
  4. 2026Sufficiency of Zeroth-Order Reward Shaping for Policy Gradient in Stabilization Controlcited by 0