paper-with-me

Papers

Numeric Reward Machines

2024-04-30 · Kristina Levina, Nikolaos Pappas, Athanasios Karapantelakis, Aneta Vulgarakis Feljan, Jendrik Seipp

Reward machines inform reinforcement learning agents about the reward structure of the environment and often drastically speed up the learning process. However, reward machines only accept Boolean features such as robot-reached-gold. Consequently, many inherently numeric tasks cannot profit from the guidance offered by reward machines. To address this gap, we aim to extend reward machines with numeric features such as distance-to-gold. For this, we present two types of reward machines: numeric-Boolean and numeric. In a numeric-Boolean reward machine, distance-to-gold is emulated by two Boolean features distance-to-gold-decreased and robot-reached-gold. In a numeric reward machine, distance-to-gold is used directly alongside the Boolean feature robot-reached-gold. We compare our new approaches to a baseline reward machine in the Craft domain, where the numeric feature is the agent-to-target distance. We use cross-product Q-learning, Q-learning with counter-factual experiences, and the options framework for learning. Our experimental results show that our new approaches significantly outperform the baseline approach. Extending reward machines with numeric features opens up new possibilities of using reward machines in inherently numeric tasks.

📄 PDF Abstract BibTeX arXiv:2404.19370

Code (0)

등록된 구현이 없습니다.

Tasks

Q-Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

Reinforcement Learning with Stochastic Reward Machines

2025-10-16 · Jan Corazza, Ivan Gavran, Daniel Neider arxiv

Reward machines are an established tool for dealing with reinforcement learning problems in which rewards are sparse and depend on complex sequences of actions. However, existing algorithms for learning reward machines a…

Reinforcement Learning

Maximally Permissive Reward Machines

2024-08-15 · Giovanni Varricchione, Natasha Alechina, Mehdi Dastani, Brian Logan

Reward machines allow the definition of rewards for temporally extended tasks and behaviors. Specifying "informative" reward machines can be challenging. One way to address this is to generate reward machines from a high…

Omega-Regular Reward Machines

2023-08-14 · Ernst Moritz Hahn, Mateo Perez, Sven Schewe, Fabio Somenzi 외

Reinforcement learning (RL) is a powerful approach for training agents to perform tasks, but designing an appropriate reward mechanism is critical to its success. However, in many cases, the complexity of the learning ob…

Reinforcement Learning (RL)

Provably Efficient Exploration in Reward Machines with Low Regret

2024-12-26 · Hippolyte Bourel, Anders Jonsson, Odalric-Ambrym Maillard, Chenxiao Ma 외

We study reinforcement learning (RL) for decision processes with non-Markovian reward, in which high-level knowledge of the task in the form of reward machines is available to the learner. We consider probabilistic rewar…

Efficient ExplorationReinforcement Learning (RL)

Pareto Q-Learning with Reward Machines

2026-06-17 · Arnaud Lequen, Clément Legrand-Lixon, Léo Saulières arxiv

We present Pareto Q-Learning with Reward Machines (PQLRM), a multi-objective reinforcement learning algorithm for tasks whose reward structure is specified by a set of reward machines (RMs). PQLRM combines Pareto Q-Learn…

Reinforcement Learning