Related papers: Goal Reasoning by Selecting Subgoals with Deep Q-L…

Goal-conditioned reinforcement learning (RL) can solve tasks in a wide range of domains, including navigation and manipulation, but learning to reach distant goals remains a central challenge to the field. Learning to reach such goals is…

The goal of meta-learning is to generalize to new tasks and goals as quickly as possible. Ideally, we would like approaches that generalize to new goals and tasks on the first attempt. Toward that end, we introduce contextual planning…

While recent work on online goal recognition efficiently infers goals under low observability, comparatively less work focuses on online goal recognition that works in both discrete and continuous domains. Online goal recognition approaches…

Learning world models offers a promising avenue for goal-conditioned reinforcement learning with sparse rewards. By allowing agents to plan actions or exploratory goals without direct interaction with the environment, world models enhance…

People are often confronted with problems whose complexity exceeds their cognitive capacities. To deal with this complexity, individuals and managers can break complex problems down into a series of subgoals. Which subgoals are most…

Pre-trained large language models have shown successful progress in many language understanding benchmarks. This work explores the capability of these models to predict actionable plans in real-world environments. Given a text instruction,…

Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because strategies interact with each other and change. Most previous work focuses on…

Goals express agents' intentions and allow them to organize their behavior based on low-dimensional abstractions of high-dimensional world states. How can agents develop such goals autonomously? This paper proposes a detailed conceptual and…

Offline Goal-Conditioned Reinforcement Learning seeks to train agents to reach specified goals from previously collected trajectories. Scaling that promises to long-horizon tasks remains challenging, notably due to compounding…

Fine-tuning large language models (LLMs) for domain-specific tasks requires training datasets that comprehensively cover the target capabilities a practitioner needs. Yet identifying which capabilities a dataset fails to support, and doing…

Temporal abstractions in the form of options have been shown to help reinforcement learning (RL) agents learn faster. However, despite prior work on this topic, the problem of discovering options through interaction with an environment…

We propose a distributed deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is based on the deep Q-network, a convolutional neural network trained…

Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects.…

Goal models have been widely used in Computer Science to represent software requirements, business objectives, and design qualities. Existing goal modelling techniques, however, have shown limitations of expressiveness and/or tractability…

An important goal of research in Deep Reinforcement Learning in mobile robotics is to train agents capable of solving complex tasks, which require a high level of scene understanding and reasoning from an egocentric perspective. When…

Goal-based investing is an approach to wealth management that prioritizes achieving specific financial goals. It is naturally formulated as a sequential decision-making problem as it requires choosing the appropriate investment until a goal…

Recently, decomposing complex problems into simple subtasks--a crucial part of human-like natural planning--to solve the given problem has significantly boosted the performance of large language models (LLMs). However, leveraging such…

We present a novel approach for image-goal navigation, where an agent navigates with a goal image rather than accurate target information, which is more challenging. Our goal is to decouple the learning of navigation goal planning,…

Machine Learning-based heuristics have recently shown impressive performance in solving a variety of hard combinatorial optimization problems (COPs). However, they generally rely on a separate neural model, specialized and trained for each…

Deep reinforcement learning includes a broad family of algorithms that parameterise an internal representation, such as a value function or policy, by a deep neural network. Each algorithm optimises its parameters with respect to an…