paper-with-me

홈 › Papers

About Time: Model-free Reinforcement Learning with Timed Reward Machines

2025-12-19 · Rajarshi Roy, Anirban Majumdar, Ritam Raha, David Parker, Marta Kwiatkowska arxiv

Reward specification plays a central role in reinforcement learning (RL), guiding the agent's behavior. To express non-Markovian rewards, formalisms such as reward machines have been introduced to capture dependencies on histories. However, traditional reward machines lack the ability to model precise timing constraints, limiting their use in time-sensitive applications. In this paper, we propose timed reward machines (TRMs), which are an extension of reward machines that incorporate timing constraints into the reward structure. TRMs enable more expressive specifications with tunable reward logic, for example, imposing costs for delays and granting rewards for timely actions. We study model-free RL frameworks (i.e., tabular Q-learning) for learning optimal policies with TRMs under digital and real-time semantics. Our algorithms integrate the TRM into learning via abstractions of timed automata, and employ counterfactual-imagining heuristics that exploit the structure of the TRM to improve the search. Experimentally, we demonstrate that our algorithm learns policies that achieve high rewards while satisfying the timing constraints specified by the TRM on popular RL benchmarks. Moreover, we conduct comparative studies of performance under different TRM semantics, along with ablations that highlight the benefits of counterfactual-imagining.

📄 PDF Abstract BibTeX arXiv:2512.17637

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Tactics of Adversarial Attack on Deep Reinforcement Learning Agents

2017-03-08 · Yen-Chen Lin, Zhang-Wei Hong, Yuan-Hong Liao, Meng-Li Shih 외

We introduce two tactics to attack agents trained by deep reinforcement learning algorithms using adversarial examples, namely the strategically-timed attack and the enchanting attack. In the strategically-timed attack, …

Adversarial AttackAtari GamesDeep Reinforcement Learningreinforcement-learning+2

Reinforcement learning with timed constraints for robotics motion planning

2025-12-31 · Zhaoan Wang, Junchao Li, Mahdi Mohammad, Shaoping Xiao arxiv

Robotic systems operating in dynamic and uncertain environments increasingly require planners that satisfy complex task sequences while adhering to strict temporal constraints. Metric Interval Temporal Logic (MITL) offer…

Reinforcement LearningMotion Planning

Reinforcement Learning for Code Optimization

2026-07-28 · Pierre Chambon, Kunhao Zheng, Juliette Decugis, Benoit Sagot 외 arxiv

RL for code correctness is now established: have the model generate a program, run it against hidden test cases, and reward solutions that pass. Extending this to code optimization seems straightforward: just add executi…

Reinforcement Learning

Adaptive Shooting for Bots in First Person Shooter Games Using Reinforcement Learning

2018-06-14 · Frank G. Glavin, Michael G. Madden

In current state-of-the-art commercial first person shooter games, computer controlled bots, also known as non player characters, can often be easily distinguishable from those controlled by humans. Tell-tale signs such …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning

2025-05-24 · Jinzheng Li, Sibo Ju, Yanzhou Su, Hongguang Li 외

Existing large language models (LLMs) driven search agents typically rely on prompt engineering to decouple the user queries into search plans, limiting their effectiveness in complex scenarios requiring reasoning. Furth…

Multiple-choicePrompt EngineeringResponse Generation