Search
Skip to Search Results- 14Exploration
- 3Reinforcement Learning
- 3Thermal conductivity
- 2Artificial Intelligence
- 2Heat flow
- 1Africa
- 1Akram, Usama
- 1Birdsell, J.M.
- 1Bixby, Rebecca J.
- 1Boston, Penelope J.
- 1Boutin, S.
- 1Cholodovskis Machado, Marlos
- 9Graduate and Postdoctoral Studies (GPS), Faculty of
- 9Graduate and Postdoctoral Studies (GPS), Faculty of/Theses and Dissertations
- 2Toolkit for Grant Success
- 2Toolkit for Grant Success/Educational Materials (Toolkit for Grant Success)
- 1Helmholtz-Alberta Initiative
- 1Helmholtz-Alberta Initiative/Journal Articles & Research Abstracts (Helmholtz-Alberta Initiative)
-
Spring 2024
Optimistic value estimates provide one mechanism for directed exploration in reinforcement learning (RL). The agent acts greedily with respect to an estimate of the value plus what can be seen as a value bonus. The value bonus can be learned by estimating a value function on reward bonuses,...
-
Spring 2016
How can the principles and concepts applied by visual communication designers be used to assist in exploring and understanding the massive, complex volumes of data now available to Digital Humanities researchers? One method we might employ to help us more easily comprehend the implications of...
-
Sample-Efficient Control with Directed Exploration in Discounted MDPs Under Linear Function Approximation
DownloadSpring 2022
An important goal of online reinforcement learning algorithms is efficient data collection to learn near-optimal behaviour, that is, optimizing the exploration-exploitation trade-off to reduce the sample-complexity of learning. To improve sample-complexity of learning it is essential that the...
-
2008-01-01
Melim, Leslie A., Northup. Diana E., Spilde, Michael N., Jones, Brian, Boston, Penelope J., Bixby, Rebecca J.
We report on a reticulated filament found in modern and fossil cave samples that cannot be correlated to any known microorganism or organism part. These filaments were found in moist environments in five limestone caves (four in New Mexico, U.S.A., one in Tabasco, Mexico), and a basalt lava tube...
-
2021-06-16
Audio recording of the NFRF-Exploration 2021 Roundtable with Evaluators. In this session, eight of the multidisciplinary review panel members who participated in the NFRF Exploration application review share their insights and tips. The evaluators talk about how reviewers assess applications and...
-
Fall 2014
Metamaterials are artificially engineered materials with tailored properties for applications in imaging, sensing, waveguiding and quantum optics. Even though they hold the potential for transformative impact, industrial applications have been impeded by large absorption losses in material...
-
1994
Movement and settlement patterns of animal offspring, along with the costs of occupying familiar and unfamiliar habitats, have been inferred frequently, but rarely have they been documented directly. To obtain such information, we monitored the individual fates of 205 (94%) of the 219 offspring...
-
Improving Deep Deterministic Policy Gradient for Sparse Reward and Goal-Conditioned Continuous Control
DownloadSpring 2024
We propose an improved version of deep deterministic policy gradient (DDPG) for sparse reward and goal-conditioned reinforcement learning. To enhance exploration, we introduce \emph{${\epsilon}{t}$-greedy}, which uses search to generate exploratory options, focusing on less-visited states. We...
-
Graphite Nanoplatelet Filler-Modified Polyurethane Nanocomposites for Thermal Transport Enhancement
DownloadFall 2017
The use of polymers in applications such as electronic packaging, heat exchangers, and thermal pastes is limited by their inability to dissipate accumulated heat effectively. Nano-scale filler modifiers may be used to improve the transport of thermal energy through polymer materials. Studies of...