Related papers: Preparing Unprepared Students For Future Learning
Better forecasts may not lead to better decision-making. To address this challenge, decision-oriented learning (DOL) has been proposed as a new branch of machine learning that replaces traditional statistical loss with a decision loss to…
Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an…
Dyna-style model-based reinforcement learning contains two phases: model rollouts to generate sample for policy learning and real environment exploration using current policy for dynamics model learning. However, due to the complex…
Prior access to domain knowledge could significantly improve the performance of a reinforcement learning agent. In particular, it could help agents avoid potentially catastrophic exploratory actions, which would otherwise have to be…
Adaptive learning systems can produce substantial learning gains, yet many students engage for too brief or too superficial a period to benefit. A central obstacle is measuring effort. Effort during multi-step problem solving is rarely…
In reinforcement learning, temporal abstraction in the action space, exemplified by action repetition, is a technique to facilitate policy learning through extended actions. However, a primary limitation in previous studies of action…
Robust policies enable reinforcement learning agents to effectively adapt to and operate in unpredictable, dynamic, and ever-changing real-world environments. Factored representations, which break down complex state and action spaces into…
This paper presents for the first time a detailed analysis of fine-grained navigation style identification in MOOCs backed by a large number of active learners. The result shows 1) whilst the sequential style is clearly in evidence, the…
Although reinforcement learning (RL) can provide reliable solutions in many settings, practitioners are often wary of the discrepancies between the RL solution and their status quo procedures. Therefore, they may be reluctant to adapt to…
Hierarchical abstractions, also known as options -- a type of temporally extended action (Sutton et. al. 1999) that enables a reinforcement learning agent to plan at a higher level, abstracting away from the lower-level details. In this…
Many of the challenges facing today's reinforcement learning (RL) algorithms, such as robustness, generalization, transfer, and computational efficiency are closely related to compression. Prior work has convincingly argued why minimizing…
In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting…
Reinforcement learning (RL) has become an increasingly active area of research in recent years. Although there are many algorithms that allow an agent to solve tasks efficiently, they often ignore the possibility that prior experience…
Robust controllers ensure stability in feedback loops designed under uncertainty but at the cost of performance. Model uncertainty in time-invariant systems can be reduced by recently proposed learning-based methods, which improve the…
Diversity of environments is a key challenge that causes learned robotic controllers to fail due to the discrepancies between the training and evaluation conditions. Training from demonstrations in various conditions can mitigate---but not…
Sequential recommendation effectively models dynamic user interests but continues to face challenges related to data sparsity. While self-supervised learning has alleviated this issue to some extent, most existing methods focus exclusively…
We study a robust alternative to empirical risk minimization called distributionally robust learning (DRL), in which one learns to perform against an adversary who can choose the data distribution from a specified set of distributions. We…
Learning from demonstration has proved itself useful for teaching robots complex skills with high sample efficiency. However, teaching long-horizon tasks with multiple skills is challenging as deviations tend to accumulate, the…
The optimal prophylaxis, and treatment if the prophylaxis fails, for a disease may be best evaluated using a sequential multiple assignment randomised trial (SMART). A SMART is a multi-stage study that randomises a participant to an initial…
Reinforcement learning algorithms have had tremendous successes in online learning settings. However, these successes have relied on low-stakes interactions between the algorithmic agent and its environment. In many settings where RL could…