Related papers: Multi-Level Discovery of Deep Options
In this work, we provide an extended discussion of a new approach to explainable Reinforcement Learning called Diverse Near-Optimal Alternatives (DNA), first proposed at L4DC 2025. DNA seeks a set of reasonable "options" for…
Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and…
In this experience report, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations. We are interested in optimizing the design of structural components, where…
We consider the problem of learning hierarchical policies for Reinforcement Learning able to discover options, an option corresponding to a sub-policy over a set of primitive actions. Different models have been proposed during the last…
We propose a new objective for option discovery that emphasizes the computational advantage of using options in planning. In a sequential machine, the speed of planning is proportional to the number of elementary operations used to achieve…
Deep active inference has been proposed as a scalable approach to perception and action that deals with large policy and state spaces. However, current models are limited to fully observable domains. In this paper, we describe a deep active…
Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In…
Direct Preference Optimisation (DPO) has emerged as a powerful method for aligning Large Language Models (LLMs) with human preferences, offering a stable and efficient alternative to approaches that use Reinforcement learning via Human…
We address the problem of learning hierarchical deep neural network policies for reinforcement learning. In contrast to methods that explicitly restrict or cripple lower layers of a hierarchy to force them to use higher-level modulating…
The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to…
We introduce MetaDOAR, a lightweight meta-controller that augments the Double Oracle / PSRO paradigm with a learned, partition-aware filtering layer and Q-value caching to enable scalable multi-agent reinforcement learning on very large…
Recent years have witnessed a tremendous improvement of deep reinforcement learning. However, a challenging problem is that an agent may suffer from inefficient exploration, particularly for on-policy methods. Previous exploration methods…
Meta-Reinforcement Learning (Meta-RL) enables fast adaptation to new testing tasks. Despite recent advancements, it is still challenging to learn performant policies across multiple complex and high-dimensional tasks. To address this, we…
Deep reinforcement learning, applied to vision-based problems like Atari games, maps pixels directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based…
In reinforcement learning, agents often learn policies for specific tasks without the ability to generalize this knowledge to related tasks. This paper introduces an algorithm that attempts to address this limitation by decomposing neural…
Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL). However, a notable limitation of DT is its reliance on recalling trajectories from datasets,…
Deep reinforcement learning for high dimensional, hierarchical control tasks usually requires the use of complex neural networks as functional approximators, which can lead to inefficiency, instability and even divergence in the training…
Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of…
A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…