arXiv research

MAPS and MAPS-SE learn from multiple suboptimal experts to improve policies efficiently.

New mirror maps improve PMD performance in reinforcement learning.

New models analyze how ECB's unconventional policies affect stock market volatility.

Thompson Sampling reduces regret in non-episodic restless bandits.

MAP-Elites generates diverse trading strategies for improved execution performance.

This paper optimizes MDP policies for efficient state aggregation.

CPR models complex decision processes by breaking them into context-specific policies, improving interpretability and accuracy.

PixL2R maps natural language to pixel-based rewards for RL, improving sample efficiency.

The paper reinterprets policy gradient methods using operator theory.

DSPI connects natural policy gradient to policy iteration, proving global convergence.

Restless bandit problems are instances of non-stationary multi-armed bandits. These problems have been studied well from the optimization perspective, where the goal is to efficiently find a near-optimal policy when system parameters are known. However, very few papers adopt a learning perspective, where the parameters…

Variational Proximal Policy Optimization improves reinforcement learning from human feedback.

In this work, we provide theoretical guarantees for reward decomposition in deterministic MDPs. Reward decomposition is a special case of Hierarchical Reinforcement Learning, that allows one to learn many policies in parallel and combine them into a composite solution. Our approach builds on mapping this problem into a…

The paper analyzes the sample complexities for policy evaluation with linear function approximation.

The paper tackles performative policy learning with strategic agents, improving scalability and generalizability.

Decomposes spillover effects under misspecified exposure mappings.

POLAR learns efficient data acquisition policies using pretrained belief representations.

In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the target task learning. We propose to adapt and reuse the mapped source task optimal-policy directly …

New approach for pricing evaluation improves on existing methods.

Novel framework for policy optimization with general parameterization and linear convergence.

New RL method learns value function for many policies using few key states.

The goal of personalized decision making is to map a unit's characteristics to an action tailored to maximize the expected outcome for that unit. Obtaining high-quality mappings of this type is the goal of the dynamic regime literature. In healthcare settings, optimizing policies with respect to a particular causal pat…

A new framework for offline RL improves policy flexibility and regularity.

PROPO tackles non-stationary MDPs with efficient policy optimization.

Wasserstein Policy Learning for Distributional Outcomes

Policy mirror ascent achieves Nash equilibrium in mean field games without a population generative model.

New methods for evaluating and optimizing policies in offline RL with unobserved confounders.

We introduce reinforcement learning for heterogeneous teams in which rewards for an agent are additively factored into local costs, stimuli unique to each agent, and global rewards, those shared by all agents in the domain. Motivating domains include coordination of varied robotic platforms, which incur different costs…

Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training…

ICIL learns policies invariant to multiple environments, improving generalization.

Bringing transparency to black-box decision making systems (DMS) has been a topic of increasing research interest in recent years. Traditional active and passive approaches to make these systems transparent are often limited by scalability and/or feasibility issues. In this paper, we propose a new notion of black-box D…

Randomized trials, also known as A/B tests, are used to select between two policies: a control and a treatment. Given a corresponding set of features, we can ideally learn an optimized policy P that maps the A/B test data features to action space and optimizes reward. However, although A/B testing provides an unbiased …

Paper analyzes neural network complexity for planning problems.

Paper uses imitation learning to create efficient insulin policies from MPC demonstrations.

Enhances PMD with lookahead to improve RL performance.

Paper optimizes learning MDPs with adversarial rewards using linear models.

Interpole learns transparent decision-making policies from data.

In this paper we propose a novel gradient algorithm to learn a policy from an expert's observed behavior assuming that the expert behaves optimally with respect to some unknown reward function of a Markovian Decision Problem. The algorithm's aim is to find a reward function such that the resulting optimal policy matche…

A new method learns the optimal pricing map for semiparametric dynamic pricing problems.

The paper analyzes off-policy TD-learning using generalized Bellman operators and provides finite-sample bounds.

This study analyzes economic policy uncertainty indices using visibility graphs.

Paper introduces CageBO for optimizing complex public policy problems.

A new method estimates multi-dimensional value distributions using Hilbert space embeddings.

The paper optimizes policies constrained to Schur stabilizing controllers using a Newton-type algorithm.

New algorithm learns policies without explicit rewards for MDPs.

Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a nov…

We decode latent states in Block MDPs and learn near-optimal policies.

We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the stat…