arXiv research

New meta-RL method avoids exploration-exploitation trade-off.

Paper develops a dynamic Bayesian approach for active learning that optimizes exploration-exploitation balance.

New AIM algorithm optimizes exploration-exploitation in bandits.

Algorithm achieves optimal pricing with minimal exploration for dynamic markets.

This research tackles balancing exploration and exploitation in deep RL for partially observable systems.

Improved Thompson Sampling for Bayesian Optimization.

Sparse reward is one of the biggest challenges in reinforcement learning (RL). In this paper, we propose a novel method called Generative Exploration and Exploitation (GENE) to overcome sparse reward. GENE automatically generates start states to encourage the agent to explore the environment and to exploit received rew…

An agent explores indefinitely in an environment with unlimited rewards.

Improved analysis of UCRL2 with empirical Bernstein inequality reduces exploration-exploitation regret.

In graph-based active learning, algorithms based on expected error minimization (EEM) have been popular and yield good empirical performance. The exact computation of EEM optimally balances exploration and exploitation. In practice, however, EEM-based algorithms employ various approximations due to the computational ha…

Proposes EE-Net for neural exploration in contextual bandits.

This paper applies Thompson Sampling to asymmetric $\alpha$-stable bandits for financial and wireless data.

XploVAE improves recommendation by balancing known and novel items.

Bayesian optimization offers the possibility of optimizing black-box operations not accessible through traditional techniques. The success of Bayesian optimization methods such as Expected Improvement (EI) are significantly affected by the degree of trade-off between exploration and exploitation. Too much exploration c…

Hyper addresses the hyperparameter tuning challenge in RL, improving exploration efficiency and robustness.

Active inference enhances RL by balancing exploration and exploitation.

Batch Thompson Sampling reduces exploration-exploitation trade-off in online decision making.

We present a new model-based algorithm for reinforcement learning (RL) which consists of explicit exploration and exploitation phases, and is applicable in large or infinite state spaces. The algorithm maintains a set of dynamics models consistent with current experience and explores by finding policies which induce hi…

Finding a good compromise between the exploitation of known resources and the exploration of unknown, but potentially more profitable choices, is a general problem, which arises in many different scientific disciplines. We propose a stylized model for these exploration-exploitation situations, including population or e…

Kernel-UCBVI algorithm balances exploration and exploitation in metric state-action spaces.

We propose a meta path planning algorithm named \emph{Neural Exploration-Exploitation Trees~(NEXT)} for learning from prior experience for solving new path planning problems in high dimensional continuous state and action spaces. Compared to more classical sampling-based methods like RRT, our approach achieves much bet…

The paper analyzes CMDPs, balancing exploration and exploitation to avoid constraint violations.

Exploration-exploitation of functions, that is learning and optimizing a mapping between inputs and expected outputs, is ubiquitous to many real world situations. These situations sometimes require us to avoid certain outcomes at all cost, for example because they are poisonous, harmful, or otherwise dangerous. We test…

Interactive user interfaces need to continuously evolve based on the interactions that a user has (or does not have) with the system. This may require constant exploration of various options that the system may have for the user and obtaining signals of user preferences on those. However, such an exploration, especiall…

Study explores strategies for randomized allocation in delayed rewards bandits.

Paper finds wide minima are better for generalization and proposes a new learning rate schedule.

We develop a coherent framework for integrative simultaneous analysis of the exploration-exploitation and model order selection trade-offs. We improve over our preceding results on the same subject (Seldin et al., 2011) by combining PAC-Bayesian analysis with Bernstein-type inequality for martingales. Such a combinatio…

New algorithm learns optimal exploration parameters for contextual bandits.

ICEE learns new RL tasks in less time with a Transformer model.

Paper proposes efficient sample collection strategy for RL.

Greedy algorithm nearly outperforms exploration in contextual bandits.

AutoML explores vs. exploits promising classifiers to improve performance.

The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to resolve the tradeoff by using a fixed exploration mechanism, such as $ε$-greedy ex…

The problem of optimizing unknown costly-to-evaluate functions has been studied for a long time in the context of Bayesian Optimization. Algorithms in this field aim to find the optimizer of the function by asking only a few function evaluations at locations carefully selected based on a posterior model. In this paper,…

In this paper, we study multi-armed bandit problems in explore-then-commit setting. In our proposed explore-then-commit setting, the goal is to identify the best arm after a pure experimentation (exploration) phase and exploit it once or for a given finite number of times. We identify that although the arm with the hig…

New strategies improve multi-agent decision-making on irregular networks.

Maximize to Explore integrates RL components for efficient policy discovery.

We introduce and analyse two algorithms for exploration-exploitation in discrete and continuous Markov Decision Processes (MDPs) based on exploration bonuses. SCAL$^+$ is a variant of SCAL (Fruit et al., 2018) that performs efficient exploration-exploitation in any unknown weakly-communicating MDP for which an upper bo…

Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world operates. One general class of algorithms for such learning is the multi-armed bandit setting. Randomized probability matching, based upon …

A new multi-objective RL framework improves intrinsic exploration performance.

In this paper, we propose and study opportunistic contextual bandits - a special case of contextual bandits where the exploration cost varies under different environmental conditions, such as network load or return variation in recommendations. When the exploration cost is low, so is the actual regret of pulling a sub-…

Active learning method improves AI performance by balancing exploration and exploitation.

Meta-SAC automatically tunes SAC's entropy temperature for better exploration.

In this paper, we propose and study opportunistic bandits - a new variant of bandits where the regret of pulling a suboptimal arm varies under different environmental conditions, such as network load or produce price. When the load/price is low, so is the cost/regret of pulling a suboptimal arm (e.g., trying a suboptim…

New algorithm improves graph-based active learning by identifying unexplored regions.

Improved UCB method for stochastic bandits using distance tuning.

Agent learns directed exploration policies to improve performance in hard games.

Proper balance between exploitation and exploration is what makes good decisions, which achieve high rewards like payoff or evolutionary fitness. The Infomax principle postulates that maximization of information directs the function of diverse systems, from living systems to artificial neural networks. While specific a…