Search
Skip to Search Results- 83Reinforcement Learning
- 17Machine Learning
- 8Artificial Intelligence
- 6Transfer Learning
- 5Planning
- 5Representation Learning
- 1Abbasi Brujeni, Lena
- 1Abbasi-Yadkori, Yasin
- 1Aghakasiri, Kiarash
- 1Alikhasi, Mahdi
- 1Asadi Atui, Kavosh
- 1Banafsheh Rafiee
-
Learning What to Remember: Strategies for Selective External Memory in Online Reinforcement Learning Agents
DownloadSpring 2019
In realistic environments, intelligent agents must learn to integrate information from their past to inform present decisions. An agent's immediate observations are often limited, and some degree of memory is necessary to complete many everyday tasks. However, an agent cannot remember everything...
-
Fall 2023
Of all the capabilities of natural intelligence, one of the most exceptional is the ability to expand upon and refine knowledge of the world through subjective experience. Therefore, a longstanding goal of Artificial Intelligence has been to replicate this success: to enable artificial agents to...
-
Fall 2023
Partial observability---when the senses lack enough detail to make an optimal decision---is the reality of any decision making agent acting in the real world. While an agent could be made to make due with its available senses, taking advantage of the history of senses can provide more context and...
-
Fall 2021
Unmanned Aerial Vehicles (UAVs), or drones, have been employed in a variety of applications, ranging from surveillance to emergency operations. These systems comprise an ”inner loop” that provides stability and control and an ”outer loop” in charge of mission-level tasks, such as way-point...
-
Fall 2022
Internal Combustion Engines (ICEs) are ubiquitous; they power a wide range of systems. The broad use of ICEs globally causes more than 20% of the total greenhouse gas emissions. In many countries, emission legislation is transitioning from certification using only traditional chassis dynomometer...
-
Spring 2022
Reinforcement learning (RL) has shown great success in solving many challenging tasks via the use of deep neural networks. Although the use of deep learning for RL brings immense representational power to the arsenal, it also causes sample inefficiency. This means that the algorithms are...
-
Fall 2022
Monte Carlo Tree Search (MCTS) is a popular tree search framework for choos- ing actions in decision-making problems. MCTS is traditionally applied to applications in which a perfect simulation model is available. However, when the model is imperfect, the performance of MCTS drops heavily. In...
-
Fall 2022
Monte Carlo Tree Search (MCTS) is an extremely successful search-based frame- work for decision making. With an accurate simulator of the environment’s dynamics, it can achieve great performance in many games and non-games applications. However, without a perfect simulator, the performance...
-
Fall 2021
The performance of reinforcement learning (RL) agents is sensitive to the choice of hyperparameters. In real-world settings like robotics or industrial control systems, however, testing different hyperparameter configurations directly on the environment can be financially prohibitive, dangerous,...
-
Fall 2021
The optimization of non-convex objective functions is a topic of central interest in machine learning. Remarkably, it has recently been shown that simple gradient-based optimization can achieve globally optimal solutions in important non-convex problems that arise in machine learning, including...