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 51 for “"Sample Efficiency"”.
-
On the Sample Efficiency of Data-Driven Decision Making
… the minimax risk, which captures the sample efficiency required for effective decision making across three key settings: offline estimation with batch data, online estimation with sequential data, and interactive decision making as exemplified by multi-armed bandits and reinforcement …
-
Advancing Language Equity and Sample Efficiency in Task-Oriented Dialogue Systems
… setups. We propose to resolve this through sample-efficient methods. For cross-lingual transfer, we harness Web-scale data to augment limited in-domain in-language resources and unlock full potential of multilingual pretrained models through layer aggregation and contrastive learning. For …
-
Interpolated Experience Replay for Improved Sample Efficiency of Model-Free Deep Reinforcement Learning Algorithms
The human brain is remarkably sample efficient, capable of learning complex behaviors given limited experience [16]. This sample efficiency property is crucial for effectively training robust deep reinforcement learning agents on continuous control tasks - when limited experience is available, poor …
-
Advancing Efficiency and Safety in Autonomous Sequential Decision Making
… substantial obstacles, chiefly in achieving sample (data) efficiency and ensuring agent safety in unpredictable, dynamic environments. Additionally, the inherent partial knowledge due to sensory and model limitations complicates agents' functionality in complex scenarios. This thesis aims to …
-
Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization
… black-box functions requires extreme sample efficiency. While Bayesian optimization (BO) is the current state-of-the-art, its performance hinges on surrogate and acquisition function hyperparameters that are often hand-tuned and fail to generalize across problem landscapes. We present …
-
On the Value of Online Learning for Cognitive Radar Waveform Selection
… inherent to the waveform selection problem, sample-efficiency and universality. Sample-efficiency corresponds to the number of experiences a learning algorithm requires to achieve desirable performance. Universality refers to the learning algorithm's ability to achieve desirable performance …
-
Value learning through Bellman residuals and neural function approximations in deterministic systems
… to the desired solution with better theoretical sample efficiency guarantees, while ADP heuristics are prone to divergence and have worse theoretical sample efficiency. On the other hand, the disadvantage of Bellman residual minimization is the requirement of two independent future samples, …
-
Offline Reward Learning from Human Demonstrations and Feedback: A Linear Programming Approach
… and offers an optimality guarantee with provable sample efficiency. One notable feature of our LP framework is the convexity of the resulting solution set, which facilitates the alignment of reward functions with human feedback, such as pairwise trajectory comparison data, while maintaining …
-
Classifying and Displaying Brain-waves through Self-supervised Learning
… and mixup techniques to improve the accuracy and sample efficiency of downstream EEG classification. Our framework combines multiple EEG datasets for self-supervised learning and uses the resulting large-scale dataset to train our proposed algorithms SeqCLR (Sequential Contrastive Learning of …
-
Sample-Efficient Reinforcement Learning for Spoken Dialogue Systems
… actions. The second challenge pertains to the sample efficiency of reinforcement learning algorithms, particularly in the context of enabling online learning with human interaction. Dialogue managers are expected to achieve effective training using minimal sample data. Model-based reinforcement …
-
Overcoming the Expressivity-Efficiency Tradeoff in Program Induction
… domain-specific performance, but are both less sample-efficient and less flexible. Large language models improve upon this sample-efficiency and domain-generality, but lack robustness and still fall far short of people and traditional approaches on difficult induction tasks. In this thesis, we …
-
Evaluating yield models for crop insurance rating
… yields from 1972-2008, this study examines in-sample goodness-of-fit measures of both the whole distribution and the insurance tail to compare a set of flexible parametric, semi-parametric, and non-parametric distributions in a meaningful economic context. Simulations are then conducted to …
-
Model-based Planning for Efficient Task Execution
… navigation benchmarks demonstrates both improved sample efficiency and transparent decision making, enabling human-in-the-loop planning and more effective human-robot collaboration.
-
Knowledge-Informed Weakly-Supervised Deep Learning Models for Cancer Applications
… image-based DL methodologies that enhance sample efficiency, predictive accuracy, and generalizability for real-world cancer applications. The proposed models systematically integrate biological, anatomical, and clinical domain knowledge into DL pipelines to overcome data scarcity and …
-
Factored State Abstraction for Option Learning
… diversity between the learned sub-policies and sample inefficiency. This thesis shows that the OC framework does not decompose problems into smaller and largely independent components, but instead increases the problem complexity with each option by considering the entire state space during …
-
Multi-fidelity Modeling and Reinforcement Learning for Energy Optimal Planning
… MFGP algorithm can incorporate many low accuracy samples from a simple motor model with a few computationally demanding battery simulations to create a single accurate energy prediction. We perform sample efficiency experiments, finding a single fidelity model often needs 10 times more high …
-
Cooperative Payload Transportation by UAVs: A Model-Based Deep Reinforcement Learning (MBDRL) Application
… navigation in a stochastic environment with a sample efficiency following that seen in single UAV work. This work has been funded by the National Science Foundation (NSF) under Award No. 2046770.
-
COMPOSITIONAL OBJECT-CENTRIC REPRESENTATIONS FOR ROBUST VISUAL PERCEPTION
… occlusion reasoning, generalization, and sample-efficient learning. To address this gap, this thesis proposes a unified object-centric representation framework with three stages: discovery, representation, and application. The proposed models improve robustness, sample efficiency, …
-
Model-based approaches for learning control from multi-modal data
… algorithms to real-world systems due to poor sample efficiency and inability to handle state and control constraints. We introduce and demonstrate a general paradigm that combines model-learning and online planning for control which can also handle a wide range of problems using traditional …
-
Mixed-precision NN accelerator with neural-hardware architecture search
… space and its exploration methodology impact efficiency and productivity. However, both architecture designs are challenging. We first propose a mixed-precision accelerator, a highly parameterized architecture that can adapt to different bit widths for different quantized layers with …
Page 1 of 3