Search Results for author:
Found 20 papers, 5 papers with code
Settling the Reward Hypothesis
The reward hypothesis posits that, "all of what we mean by goals and purposes can be well thought of as maximization of the expected value of the cumulative sum of a received scalar signal (reward)."
Meta-Gradients in Non-Stationary Environments
We support these results with a qualitative analysis of resulting meta-parameter schedules and learned functions of context features.
A Theory of Abstraction in Reinforcement Learning
Reinforcement learning defines the problem facing agents that learn to make good decisions through action and observation alone.
On the Expressivity of Markov Reward
We then provide a set of polynomial-time algorithms that construct a Markov reward function that allows an agent to optimize tasks of each of these three types, and correctly determine when no such reward function exists.
Bad-Policy Density: A Measure of Reinforcement Learning Hardness
We address this question by proposing a simple measure of reinforcement-learning hardness called the bad-policy density.
People construct simplified mental representations to plan
We propose a computational account of this simplification process and, in a series of pre-registered behavioral experiments, show that it is subject to online cognitive control and that people optimally balance the complexity of a task representation and its utility for planning and acting.
Revisiting Peng's Q($λ$) for Modern Reinforcement Learning
These results indicate that Peng's Q($\lambda$), which was thought to be unsafe, is a theoretically-sound and practically effective algorithm.
What can I do here? A Theory of Affordances in Reinforcement Learning
Gibson (1977) coined the term "affordances" to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents.
The Efficiency of Human Cognition Reflects Planned Information Processing
Thus, people should plan their actions, but they should also be smart about how they deploy resources used for planning their actions.
Learning State Abstractions for Transfer in Continuous Control
In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good representations" to be a learned state abstraction, and "challenging problems" to be continuous control tasks.
Lipschitz Lifelong Reinforcement Learning
We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks.
Discovering Options for Exploration by Minimizing Cover Time
One of the main challenges in reinforcement learning is solving tasks with sparse reward.
Mitigating Planner Overfitting in Model-Based Reinforcement Learning
An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model.
Model-based Reinforcement Learning
reinforcement-learning
+1
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.
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.
Modeling Latent Attention Within Neural Networks
Deep neural networks are able to solve tasks across a variety of domains and modalities of data.
Agent-Agnostic Human-in-the-Loop Reinforcement Learning
Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning.
Near Optimal Behavior via Approximate State Abstraction
The combinatorial explosion that plagues planning and reinforcement learning (RL) algorithms can be moderated using state abstraction.
Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains
We address both of these challenges with two complementary techniques: First, we develop a gradient-boosting style, non-parametric function approximator for learning on $Q$-function residuals.
