Related papers: Reciprocal Learning
Lately, there has been a resurgence of interest in using supervised learning to solve reinforcement learning problems. Recent work in this area has largely focused on learning command-conditioned policies. We investigate the potential of…
We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and…
Passive observational data, such as human videos, is abundant and rich in information, yet remains largely untapped by current RL methods. Perhaps surprisingly, we show that passive data, despite not having reward or action labels, can…
Inverse reinforcement learning is the problem of inferring a reward function from an optimal policy or demonstrations by an expert. In this work, it is assumed that the reward is expressed as a reward machine whose transitions depend on…
Typical models of learning assume incremental estimation of continuously-varying decision variables like expected rewards. However, this class of models fails to capture more idiosyncratic, discrete heuristics and strategies that people and…
Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…
This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent. The principal and the agent have misaligned objectives and the choice of action is only left to the…
Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area…
In many machine learning applications, there are multiple decision-makers involved, both automated and human. The interaction between these agents often goes unaddressed in algorithmic development. In this work, we explore a simple version…
Current reinforcement learning algorithms train an agent using forward-generated trajectories, which provide little guidance so that the agent can explore as much as possible. While realizing the value of reinforcement learning results from…
Classical learning assumes the learner is given a labeled data sample, from which it learns a model. The field of Active Learning deals with the situation where the learner begins not with a training sample, but instead with resources that…
Social learning is learning through the observation of or interaction with other individuals; it is critical in the understanding of the collective behaviors of humans in social physics. We study the learning process of agents in a restless…
The theory of reinforcement learning has focused on two fundamental problems: achieving low regret, and identifying $\epsilon$-optimal policies. While a simple reduction allows one to apply a low-regret algorithm to obtain an…
Reinforcement learning algorithms are generally designed to maximize the expected return across a population. However, a policy that is optimal on average may be suboptimal for certain individuals, leading to potential safety concerns. To…
Humans can continuously learn new knowledge. However, machine learning models suffer from drastic dropping in performance on previous tasks after learning new tasks. Cognitive science points out that the competition of similar knowledge is…
In modern ML Ops environments, model deployment is a critical process that traditionally relies on static heuristics such as validation error comparisons and A/B testing. However, these methods require human intervention to adapt to…
We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…
We study the multi-task learning problem that aims to simultaneously analyze multiple datasets collected from different sources and learn one model for each of them. We propose a family of adaptive methods that automatically utilize…
Machine learning algorithms are used to construct a mathematical model for a system based on training data. Such a model is capable of making highly accurate predictions without being explicitly programmed to do so. These techniques have a…
Continuously learning and leveraging the knowledge accumulated from prior tasks in order to improve future performance is a long standing machine learning problem. In this paper, we study the problem in the multi-armed bandit framework with…