Hierarchies of reward machines
Reward machines (RMs) are a recent formalism for representing the reward function of a
reinforcement learning task through a finite-state machine whose edges encode subgoals of …
reinforcement learning task through a finite-state machine whose edges encode subgoals of …
Regular Reinforcement Learning
In reinforcement learning, an agent incrementally refines a behavioral policy through a
series of episodic interactions with its environment. This process can be characterized as …
series of episodic interactions with its environment. This process can be characterized as …
Exploration in reward machines with low regret
H Bourel, A Jonsson, OA Maillard… - International …, 2023 - proceedings.mlr.press
We study reinforcement learning (RL) for decision processes with non-Markovian reward, in
which high-level knowledge in the form of reward machines is available to the learner …
which high-level knowledge in the form of reward machines is available to the learner …
Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks
Improving sample efficiency is central to Reinforcement Learning (RL), especially in
environments where the rewards are sparse. Some recent approaches have proposed to …
environments where the rewards are sparse. Some recent approaches have proposed to …
[PDF][PDF] Intention Progression with Temporally Extended Goals
Abstract The Belief-Desire-Intention (BDI) approach to agent development has formed the
basis for much of the research on architectures for autonomous agents. A key advantage of …
basis for much of the research on architectures for autonomous agents. A key advantage of …
[PDF][PDF] Empowering BDI Agents with Generalised Decision-Making
RF Pereira, F Meneguzzi - … of the 23rd International Conference on …, 2024 - aura.abdn.ac.uk
Research on autonomous agents has long been concerned with reasoning about an agent's
actions within an environment [35], regardless of the underlying agent architecture [15] …
actions within an environment [35], regardless of the underlying agent architecture [15] …
Learning Reward Machines in Cooperative Multi-agent Tasks
This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that
combines cooperative task decomposition with the learning of Reward Machines (RMs) …
combines cooperative task decomposition with the learning of Reward Machines (RMs) …
[PDF][PDF] Multi-agent intention recognition and progression
For an agent in a multi-agent environment, it is often beneficial to be able to predict what
other agents will do next when deciding how to act. Previous work in multi-agent intention …
other agents will do next when deciding how to act. Previous work in multi-agent intention …
[PDF][PDF] Feedback-Guided Intention Scheduling for BDI Agents
Intelligent agents, like those based on the popular BDI agent paradigm, typically pursue
multiple goals in parallel. An intention scheduler is required to reason about the possible …
multiple goals in parallel. An intention scheduler is required to reason about the possible …
[PDF][PDF] Comparing Variable Handling Strategies in BDI Agents: Experimental Study.
BDI (Belief-Desire-Intention) agents represent a paradigm in artificial intelligence,
demonstrating proficiency in reasoning, planning, and decision-making. They offer a …
demonstrating proficiency in reasoning, planning, and decision-making. They offer a …