Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 28 for “"goal-conditioned"”.
-
Learning goal-conditioned in-hand object re-orientation
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01
-
GRLSR : a goal-conditioned RL related state representation learning method
… of the methods used. This paper introduces a goal-conditioned RL related state representation learning method (GRLSR) for learning the embedding of states without using reward or action datasets. We treat representation learning as a goal-conditioned RL problem with binary reward and devise …
-
Learning-Free Methods for Goal Conditioned Reinforcement Learning from Images
We are interested in training goal-conditioned reinforcement learning agents to reach arbitrary goals specified as images. In order to make our agent fully general, we provide the agent with only images of the environment and the goal image. Prior methods in goal-conditioned reinforcement learning …
-
Quasimetric decision transformer: enhancing goal-conditioned reinforcement learning with structured distance guidance
… heuristically defined and often suboptimal for goal-conditioned tasks. In this work, we introduce Quasimetric Decision Transformer (QuaD), a novel approach that replaces RTG with learned quasimetric distances, providing a more structured and theoretically grounded guidance signal for …
-
Goal-Conditioned Evaluation of Sustainable Development Goal Contributions in Theses and Dissertations
… to a United Nations Sustainable Development Goal (SDG) requires reasoning about how the document's claims, methods, and findings relate to the targets that define the goal, a teleological judgment that depends on the evaluator's interpretive framework rather than on the document's content …
-
Learning from Pixels: Image-Centric State Representation Reinforcement Learning for Goal Conditioned Surgical Task Automation
Over the past few years, significant exploration has occurred in the field of automating surgical tasks through off-policy Reinforcement Learning (RL) methods. These methods have witnessed notable advancements in enhancing sample efficiency (such as with the use of Hindsight Experience Replay - …
-
Training Agents to Achieve Goals
This thesis is about training agents to achieve goals. Traditional reinforcement learning agents learn to maximize a reward signal that is often hand-engineered for a specific task. In contrast, goal-conditioned reinforcement learning creates more generalist agents by allowing a user to specify a …
-
Generating Legible Robot Motion From Classifier Guided Diffusion Policies
… motion that conveys a robot’s intentions and goals is known to improve safety, task efficiency, and user experience. Legible robot motion is typically generated using hand-designed cost functions and classical motion planners. However, with the rise of deep learning and data-driven robot …
-
Enhancing Realism in Indoor Navigation
… reconstruction and policy learning to advance goal-conditioned navigation in complex environments. The first of the works presents a novel framework that integrates 3D Gaussian Splatting with smartphone-based captures to create high-fidelity simulation environments. Our approach enables faster …
-
Curating Visual Information in Sequential Decision Making Problems
… some objective. These settings include goal-conditioned object retrieval in a simulated kitchen, part-based assembly problems using LEGO bricks, and escaping giant monsters in the first-person video game DOOM. In all of these settings, we show that by carefully considering an agent’s …
-
Variational methods for probabilistic inference and decision-making
… and improves the performance of RL agents in goal-conditioned sequential decision-making tasks. Overall, this thesis presents probabilistically principled, practical methods for making neural networks more reliable and more suitable for deployment in high-stakes, safety-critical environments.
-
Foundation Reward Models for Robot Learning
… reinforcement learning algorithm that learns goal-conditioned value functions from unstructured human videos, enabling zero-shot reward generation for unseen robot tasks specified in image or language modalities, and (2) a framework combining large language models with search to automatically …
-
Towards Better Efficiency and Generalization in Imitation Learning: A Causal Perspective
… introduces a novel method to enhance goal-conditioned imitation learning using Structural Causal Models (SCMs) and counterfactual data. We leverage SCMs as a formalism to understand the inherent causal relationships between different variables governing expert behavior. This enables …
-
Multimodal Learning-Based Frameworks for Sensor-Free Force-Aware Perception and Autonomous Navigation in Cardiac Catheterization
… three-dimensional contact forces and support goal-directed navigation. A lightweight fusion-based convolutional neural network is first proposed to estimate three-dimensional contact forces directly from stereo catheter images without reliance on physical sensors or explicit mechanical …
-
On Deep Learning for Nonprehensile Manipulation
… Action Map action space, selects strategic subgoals, which are then executed by a low-level, goal-conditioned diffusion policy. Extensive experiments in the Box-Delivery task demonstrate that HeRD significantly outperforms both state-of-the-art learning-based methods (SAM) and classical motion …
-
Reward is not Necessary: Foundations for Compositional Non-Stationary Non-Markovian Hierarchical Planning\\ and Intrinsically Motivated Autonomous Agents
… and algorithms to determine the value of goals and plan into the future within a product-space of variables, especially when some of the variables (e.g. physiological variables) have the potential undermine their autonomy if not regulated. Ideally, agents should also be able to exploit …
-
Development of deep learning methods for efficient exploration of ultra-large chemical spaces
… expert demonstrations from drug-like data, then goal-conditioned finetuning, A-GFN generates novel compounds with high predicted binding affinity while maintaining synthetic feasibility and drug-likeness. Collectively, these methods form a comprehensive toolkit combining graph neural networks, …
-
Physics-Informed Dynamic 3D Reconstruction: From Gaussian Splatting and Rigid-Body Simulation to Inverse Material Estimation
… particle field parallels the 3DGS primitive. A goal-conditioned reinforcement learning policy in a normalizing-flow latent space amortizes estimation across arbitrary targets, achieving 0.642 simulator-validated recovery in a single pass, while a warm-start hybrid reaches the highest overall …
-
Simulation Driven Multimodal Imitation Learning Based Navigation for Unstructured Corn Crop Field Environment
… combines RGB imagery, LiDAR measurements, and goal-conditioned representations within a unified policy architecture that directly predicts navigation commands from multimodal observations. To improve robustness and reduce the effects of covariate shift commonly associated with behavior cloning, …
Page 1 of 2