arXiv research

Optimizes biomolecular simulations by ranking adaptive sampling policies.

New model-based methods adapt pre-trained policies to unseen environments efficiently.

We propose a new concept named adaptive submodularity ratio to study the greedy policy for sequential decision making. While the greedy policy is known to perform well for a wide variety of adaptive stochastic optimization problems in practice, its theoretical properties have been analyzed only for a limited class of p…

Adaptive reduction scheme approximates optimal policy in regularized MDPs.

Accelerates policy optimization in RL with optimistic and adaptive updates.

FLAP adapts policies quickly to new tasks using shared linear representations.

Adaptive exploration scheme for evaluating multiple policies with different rewards.

Adaptive sequential decision making is one of the central challenges in machine learning and artificial intelligence. In such problems, the goal is to design an interactive policy that plans for an action to take, from a finite set of $n$ actions, given some partial observations. It has been shown that in many applicat…

Offline RL policies should adapt to unknown aspects of the environment.

Adapting policy learning for data collected from evolving systems.

AdaRL improves robust RL by adaptively adjusting policy complexity.

Adapts model-based advice to stabilize black-box policies for nonlinear control.

Very recently proximal policy optimization (PPO) algorithms have been proposed as first-order optimization methods for effective reinforcement learning. While PPO is inspired by the same learning theory that justifies trust region policy optimization (TRPO), PPO substantially simplifies algorithm design and improves da…

Step-DAD improves BED by periodically updating a design policy during experiments.

Paper proposes a new DR estimator for adaptive experiments with improved performance.

We consider the problem of group testing with sum observations and noiseless answers, in which we aim to locate multiple objects by querying the number of objects in each of a sequence of chosen sets. We study a probabilistic setting with entropy loss, in which we assume a joint Bayesian prior density on the locations …

Meta-reinforcement learning improves fault-adaptive control efficiency.

Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provide…

ReCAP adapts to dynamic financial markets by segmenting and combining policy vectors.

Paper proposes a new method to optimize robot body structure and control policy.

Study on learning strategies in adaptive Markov games with policy regret as metric.

LALR adapts learning rate for faster convergence in regression and neural nets.

AdaRL adapts quickly to new environments with minimal data.

Meta-Reinforcement learning approaches aim to develop learning procedures that can adapt quickly to a distribution of tasks with the help of a few examples. Developing efficient exploration strategies capable of finding the most useful samples becomes critical in such settings. Existing approaches towards finding effic…

Adapts GRPO for off-policy RL, improving reward.

Develops adaptive framework for estimating survival effects with censoring.

Study optimizes experimental design for best treatment arm identification.

Adaptive inference for $M$-estimators in bandit data with model misspecification.

The paper improves DR estimators for off-policy evaluation in contextual bandits.

We propose a novel approach to address one aspect of the non-stationarity problem in multi-agent reinforcement learning (RL), where the other agents may alter their policies due to environment changes during execution. This violates the Markov assumption that governs most single-agent RL methods and is one of the key c…

New methods for anytime-valid off-policy inference in contextual bandits.

Deep reinforcement learning finds optimal learning policies for adaptive systems.

New guarantees for ERM with adaptively collected data.

In this paper we consider the basic version of Reinforcement Learning (RL) that involves computing optimal data driven (adaptive) policies for Markovian decision process with unknown transition probabilities. We provide a brief survey of the state of the art of the area and we compare the performance of the classic UCB…

We consider the core reinforcement-learning problem of on-policy value function approximation from a batch of trajectory data, and focus on various issues of Temporal Difference (TD) learning and Monte Carlo (MC) policy evaluation. The two methods are known to achieve complementary bias-variance trade-off properties, w…

New algorithm learns optimal policy with multi-step lookahead information.

In real-world machine learning applications, there is a cost associated with sampling of different features. Budgeted learning can be used to select which feature-values to acquire from each instance in a dataset, such that the best model is induced under a given constraint. However, this approach is not possible in th…

Paper optimizes Bayesian optimization for complex functions with macro-actions.

Estimators computed from adaptively collected data do not behave like their non-adaptive brethren. Rather, the sequential dependence of the collection policy can lead to severe distributional biases that persist even in the infinite data limit. We develop a general method -- $\mathbf{W}$-decorrelation -- for transformi…

IntelligentPooling learns personalized mHealth policies from limited data.

We consider a multi-armed bandit problem in a setting where each arm produces a noisy reward realization which depends on an observable random covariate. As opposed to the traditional static multi-armed bandit problem, this setting allows for dynamically changing rewards that better describe applications where side inf…

iDAD uses neural networks to quickly adapt experiments without likelihoods.

Paper presents a method for efficient robot adaptation using fine-tuning.

New method optimizes policies in non-stationary environments.

The paper sets bounds on how much regret is unavoidable in adaptive LQR with unknown B-matrix.

We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-…

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…

CADR estimator improves inference for contextual bandit data.