arXiv research

Paper tackles action selection in deep RL, proposing a data-driven approach.

Simplifies large action space bandits by selecting representative actions.

We introduce a new online learning framework where, at each trial, the learner is required to select a subset of actions from a given known action set. Each action is associated with an energy value, a reward and a cost. The sum of the energies of the actions selected cannot exceed a given energy budget. The goal is to…

Solves action selection for large spaces in RL, achieving near-optimal performance.

We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) algorithms especially when the number of items is huge. In this paper, we present …

In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would otherwise be hard to achieve when using single action selection techniques. We use both …

Algorithm optimizes multi-player learning with noisy rewards without direct communication.

Investors with asymmetric information play a game to optimize their portfolios.

Configuration spaces for computer systems can be challenging for traditional and automatic tuning strategies. Injecting task-specific knowledge into the tuner for a task may allow for more efficient exploration of candidate configurations. We apply this idea to the task of index set selection to accelerate database wor…

Paper tackles policy selection in offline RL without hyperparameters.

Active inference selects actions to maximize information gain, aiding structure learning.

POTEC tackles off-policy learning in large action spaces, improving effectiveness.

A new RL approach learns near-equivalent actions for healthcare decisions.

New method for linear bandits with unknown sparsity, improving sparse regret bounds.

Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings. Many important settings involve discrete actions, however, and so here we derive an alternative version of the Soft Actor-Critic algorithm that is applicable to dis…

Lower bounds on eigenspectrum show rich action spaces force polynomial regret in linear bandits.

New methods use vector search and nearest-neighbor matching for policy learning in causal inference.

As Computer Vision moves from a passive analysis of pixels to active analysis of semantics, the breadth of information algorithms need to reason over has expanded significantly. One of the key challenges in this vein is the ability to identify the information required to make a decision, and select an action that will …

New method reduces bias in learning from large action spaces using selective importance sampling.

Paper proposes interpretable RL policies from a mixture of experts.

A new algorithm for cryo-EM data collection that balances reward and latency.

A new method for sparse linear bandits reduces exploration-exploitation tradeoff.

New reinforcement learning framework for adapting to new actions.

Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and hand-crafted perceptual models. In this work we propose an end-to-end differentiable meth…

We discuss the relative merits of optimistic and randomized approaches to exploration in reinforcement learning. Optimistic approaches presented in the literature apply an optimistic boost to the value estimate at each state-action pair and select actions that are greedy with respect to the resulting optimistic value f…

Interactive machine learning improves learning efficiency with user input.

Exploration is a fundamental aspect of Reinforcement Learning, typically implemented using stochastic action-selection. Exploration, however, can be more efficient if directed toward gaining new world knowledge. Visit-counters have been proven useful both in practice and in theory for directed exploration. However, a m…

Construct spectral triples on C*-algebras with group actions.

Agents acting in the natural world aim at selecting appropriate actions based on noisy and partial sensory observations. Many behaviors leading to decision mak- ing and action selection in a closed loop setting are naturally phrased within a control theoretic framework. Within the framework of optimal Control Theory, o…

ReLEX algorithm improves RL efficiency by selecting optimal representations.

Improved action recognition in live videos with hybrid FR-DL method.

Interactive RL and DT feedback improve feature selection efficiency.

Selective state-adaptive regularization improves offline RL performance.

MaxMax Q-Learning improves coordination in multi-agent reinforcement learning by refining action selection.

New metrics help rebuild trust in Active Learning for industry practitioners.

New action poisoning attacks improve LinUCB's performance by changing action signals.

New probabilistic approaches offer recourse recommendations even when causal models are imperfect.

Extends Thompson sampling for RL with fewer episodes.

Algorithm optimizes bandit decisions with changing action sets using Gaussian processes.

Optimizes predictions for specific tasks using parametrized decision analysis.

Epistasis (gene-gene interaction) is crucial to predicting genetic disease. Our work tackles the computational challenges faced by previous works in epistasis detection by modeling it as a one-step Markov Decision Process where the state is genome data, the actions are the interacted genes, and the reward is an interac…

This paper extends combinatorial semi-bandits to graph feedback, improving regret bounds.

The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant expert demonstrations or the explicitly-coded cost function on targe…

The study proposes using TD error for selecting σ in Q(σ, λ).

A policy is said to be robust if it maximizes the reward while considering a bad, or even adversarial, model. In this work we formalize two new criteria of robustness to action uncertainty. Specifically, we consider two scenarios in which the agent attempts to perform an action $a$, and (i) with probability $α$, an alt…

New algorithm optimizes online decision-making with dynamically generated actions.

The paper shows how expert knowledge can improve treatment effect estimation.

Random small feature subsets outperform FS in diverse datasets.