Search Results for author:
Found 24 papers, 3 papers with code
Selecting Context Clozes for Lightweight Reading Compliance
We explore a novel approach to reading compliance, leveraging large language models to select inline challenges that discourage skipping during reading.
Explaining Why: How Instructions and User Interfaces Impact Annotator Rationales When Labeling Text Data
In the context of data labeling, NLP researchers are increasingly interested in having humans select rationales, a subset of input tokens relevant to the chosen label.
Computably Continuous Reinforcement-Learning Objectives are PAC-learnable
In particular, for the analysis that considers only sample complexity, we prove that if an objective given as an oracle is uniformly continuous, then it is PAC-learnable.
Model-based Lifelong Reinforcement Learning with Bayesian Exploration
We propose a model-based lifelong reinforcement-learning approach that estimates a hierarchical Bayesian posterior distilling the common structure shared across different tasks.
Meta-Learning Parameterized Skills
We propose a novel parameterized skill-learning algorithm that aims to learn transferable parameterized skills and synthesize them into a new action space that supports efficient learning in long-horizon tasks.
Does DQN really learn? Exploring adversarial training schemes in Pong
In this work, we study two self-play training schemes, Chainer and Pool, and show they lead to improved agent performance in Atari Pong compared to a standard DQN agent -- trained against the built-in Atari opponent.
Learning Generalizable Behavior via Visual Rewrite Rules
Though deep reinforcement learning agents have achieved unprecedented success in recent years, their learned policies can be brittle, failing to generalize to even slight modifications of their environments or unfamiliar situations.
On the (In)Tractability of Reinforcement Learning for LTL Objectives
In recent years, researchers have made significant progress in devising reinforcement-learning algorithms for optimizing linear temporal logic (LTL) objectives and LTL-like objectives.
Reinforcement Learning with General LTL Objectives is Intractable
In recent years, researchers have made significant progress in devising reinforcement-learning algorithms for optimizing linear temporal logic (LTL) objectives and LTL-like objectives.
Learning Finite Linear Temporal Logic Specifications with a Specialized Neural Operator
Finite linear temporal logic ($\mathsf{LTL}_f$) is a powerful formal representation for modeling temporal sequences.
Coarse-Grained Smoothness for RL in Metric Spaces
We propose a new coarse-grained smoothness definition that generalizes the notion of Lipschitz continuity, is more widely applicable, and allows us to compute significantly tighter bounds on Q-functions, leading to improved learning.
Bayesian Exploration for Lifelong Reinforcement Learning
A central question in reinforcement learning (RL) is how to leverage prior knowledge to accelerate learning in new tasks.
Model Selection's Disparate Impact in Real-World Deep Learning Applications
Algorithmic fairness has emphasized the role of biased data in automated decision outcomes.
Task Scoping: Generating Task-Specific Abstractions for Planning in Open-Scope Models
Unfortunately, planning to solve any specific task using an open-scope model is computationally intractable - even for state-of-the-art methods - due to the many states and actions that are necessarily present in the model but irrelevant to that problem.
Teaching with IMPACT
Like many problems in AI in their general form, supervised learning is computationally intractable.
ReNeg and Backseat Driver: Learning from Demonstration with Continuous Human Feedback
Our framework learns continuous control from sub-optimal demonstration and evaluative feedback collected before training.
Measuring and Characterizing Generalization in Deep Reinforcement Learning
We re-examine what is meant by generalization in RL, and propose several definitions based on an agent's performance in on-policy, off-policy, and unreachable states.
Finding Options that Minimize Planning Time
We formalize the problem of selecting the optimal set of options for planning as that of computing the smallest set of options so that planning converges in less than a given maximum of value-iteration passes.
Personalized Education at Scale
Tailoring the presentation of information to the needs of individual students leads to massive gains in student outcomes~\cite{bloom19842}.
Policy and Value Transfer in Lifelong Reinforcement Learning
We consider the problem of how best to use prior experience to bootstrap lifelong learning, where an agent faces a series of task instances drawn from some task distribution.
State Abstractions for Lifelong Reinforcement Learning
We introduce two new classes of abstractions: (1) transitive state abstractions, whose optimal form can be computed efficiently, and (2) PAC state abstractions, which are guaranteed to hold with respect to a distribution of tasks.
Mean Actor Critic
We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning.
Ranked #1 on
Continuous Control
on Cart Pole (OpenAI Gym)
Showing versus doing: Teaching by demonstration
Stark differences arise when demonstrators are intentionally teaching a task versus simply performing a task.
