arXiv research

Quantum UCB algorithm reduces reinforcement learning regret exponentially.

Unified framework for model- and value-optimistic reinforcement learning.

New rule reduces exploration regret to logarithmic, improving bad episode handling.

Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for high-stakes applications like healthcare. This paper introduces a new framework for theoretically measuring the performance of such algorithms called Uniform-PAC, which is a strengthening of the classical Probably Approximatel…

Improved reinforcement learning for episodes with varying action sets.

We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic bandits. We provide a framework which modifies the aggressive exploration enjoyed b…

In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform …

Paper proposes RRD to learn proxy rewards for sparse delayed rewards in episodic reinforcement learning.

New framework for RL with linear-convex models reduces performance gap.

New framework for reinforcement learning with sporadic state observations.

We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories ar…

New framework for reinforcement learning with adversarial preferences in tabular MDPs.

Study preference-based reinforcement learning in episodic kernel MDPs.

Timely prediction of clinically critical events in Intensive Care Unit (ICU) is important for improving care and survival rate. Most of the existing approaches are based on the application of various classification methods on explicitly extracted statistical features from vital signals. In this work, we propose to elim…

Algorithm tackles constrained reinforcement learning with concave-convex and knapsack constraints.

Algorithm improves multi-armed bandit performance by transferring reward samples.

PredictionMarketBench benchmarks trading agents on prediction markets.

The paper interprets financial markets as crowds during booms and busts.

BerlinUCB learns from episodic rewards in nonstationary contexts.

Thompson Sampling reduces regret in non-episodic restless bandits.

Improved regret bound for online learning in unknown MDPs.

In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained on episodes representing different c…

A new framework improves few-shot classification by learning to generalize to unseen classes.

Algorithm reduces episode count for CMDPs with constraints.

Many interesting real world domains involve reinforcement learning (RL) in partially observable environments. Efficient learning in such domains is important, but existing sample complexity bounds for partially observable RL are at least exponential in the episode length. We give, to our knowledge, the first partially …

Algorithm improves online learning in adversarial bandits.

Study evaluates policies in partially observable environments without full model specification.

New algorithm learns reward signals from episodic returns for better reinforcement learning.

Reinforcement learning (RL) algorithms have made huge progress in recent years by leveraging the power of deep neural networks (DNN). Despite the success, deep RL algorithms are known to be sample inefficient, often requiring many rounds of interaction with the environments to obtain satisfactory performance. Recently,…

We introduce a new class of reinforcement learning methods referred to as {\em episodic multi-armed bandits} (eMAB). In eMAB the learner proceeds in {\em episodes}, each composed of several {\em steps}, in which it chooses an action and observes a feedback signal. Moreover, in each step, it can take a special action, c…

Model learns continuously from text without forgetting.

Paper proposes DAC-ML, a cognitive architecture that learns quickly from few episodes.

This paper finds an MFE in large stochastic games using reinforcement learning.

We present an actor-critic framework for MDPs where the objective is the variance-adjusted expected return. Our critic uses linear function approximation, and we extend the concept of compatible features to the variance-adjusted setting. We present an episodic actor-critic algorithm and show that it converges almost su…

Enhanced image recognition models learn from human-like memory and shape biases.

In this paper we address the problem of discovering a small set of frequent serial episodes from sequential data so as to adequately characterize or summarize the data. We discuss an algorithm based on the Minimum Description Length (MDL) principle and the algorithm is a slight modification of an earlier method, called…

We propose Episodic Backward Update (EBU) - a novel deep reinforcement learning algorithm with a direct value propagation. In contrast to the conventional use of the experience replay with uniform random sampling, our agent samples a whole episode and successively propagates the value of a state to its previous states.…

Recurrent major mood episodes and subsyndromal mood instability cause substantial disability in patients with bipolar disorder. Early identification of mood episodes enabling timely mood stabilisation is an important clinical goal. Recent technological advances allow the prospective reporting of mood in real time enabl…

New framework finds periodic policies in reset-free MDPs with sublinear regret.

New algorithms reduce dynamic regret in online MDPs with changing losses.

Extends Thompson sampling for RL with fewer episodes.

Single episode policy transfer in RL without access to rewards.

Paper proposes new $γ$-regret measure for non-episodic RL.

Paper proposes DAPNA to improve few-shot learning with domain adaptation.

New algorithm for average reward learning with bounded hitting time assumption.

This paper explores how environmental properties can simplify reinforcement learning in non-episodic settings.

New schemes improve lifelong learning by balancing old and new tasks.

Deep RNN detects FoG episodes in Parkinson's disease with high accuracy.