arXiv research

Paper optimizes industrial refrigeration using adaptive exploration.

New method uses birth-death process and exploration component to accelerate sampling from multimodal distributions.

In classical reinforcement learning, when exploring an environment, agents accept arbitrary short term loss for long term gain. This is infeasible for safety critical applications, such as robotics, where even a single unsafe action may cause system failure. In this paper, we address the problem of safely exploring fin…

Reinforcement learning algorithms rely on exploration to discover new behaviors, which is typically achieved by following a stochastic policy. In continuous control tasks, policies with a Gaussian distribution have been widely adopted. Gaussian exploration however does not result in smooth trajectories that generally c…

Efficient Reinforcement Learning usually takes advantage of demonstration or good exploration strategy. By applying posterior sampling in model-free RL under the hypothesis of GP, we propose Gaussian Process Posterior Sampling Reinforcement Learning(GPPSTD) algorithm in continuous state space, giving theoretical justif…

This paper studies systematic exploration for reinforcement learning with rich observations and function approximation. We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our first contribution is a complexity measure, the Bellman rank, that we show enables …

Paper presents an algorithm for optimal regret in communicating Markov decision processes.

The outcome of the explorative data analysis (EDA) phase is vital for successful data analysis. EDA is more effective when the user interacts with the system used to carry out the exploration. In the recently proposed paradigm of iterative data mining the user controls the exploration by inputting knowledge in the form…

A new active learning method for Gaussian process models.

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

This paper proposes a method to safely adjust exploration in RL to satisfy constraints.

Enhanced Gaussian process models accelerate optimization and posterior approximation.

Regularization-induced exploration improves contextual bandit performance.

Optimally explores dynamical systems with varying properties using context inference.

Context. Generative models open up the possibility to interrogate scientific data in a more data-driven way. Aims: We propose a method that uses generative models to explore hypotheses in astrophysics and other areas. We use a neural network to show how we can independently manipulate physical attributes by encoding ob…

Study minimax optimal RL in factored MDPs with bonus exploration.

Random exploration optimizes Bayesian optimization with optimal error rates and computational efficiency.

We introduce the active exploration problem in Markov decision processes (MDPs). Each state of the MDP is characterized by a random value and the learner should gather samples to estimate the mean value of each state as accurately as possible. Similarly to active exploration in multi-armed bandit (MAB), states may have…

New framework uses unsupervised learning for efficient exploration in RL.

Improved Bayesian optimisation method using randomised Gaussian process UCB.

The paper explores risk-minimization for exponential additive models, providing mathematical expressions and numerical examples.

StepMix algorithm ensures safe exploration in reinforcement learning with near-optimal performance.

Maximize to Explore integrates RL components for efficient policy discovery.

GPR enhances materials discovery by automating parameter space exploration.

Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.

The paper tackles efficient exploration in MDPs to learn accurate models.

BOKE optimizes expensive functions with reduced computational costs.

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…

Study improves posterior inference in neural processes with limited data.

A fundamental issue in reinforcement learning algorithms is the balance between exploration of the environment and exploitation of information already obtained by the agent. Especially, exploration has played a critical role for both efficiency and efficacy of the learning process. However, Existing works for explorati…

We introduce Parameterized Exploration (PE), a simple family of methods for model-based tuning of the exploration schedule in sequential decision problems. Unlike common heuristics for exploration, our method accounts for the time horizon of the decision problem as well as the agent's current state of knowledge of the …

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…

Bayesian RL enhances LLMs to reflectively explore and correct errors.

We present a class of Lévy processes for modelling financial market fluctuations: Bilateral Gamma processes. Our starting point is to explore the properties of bilateral Gamma distributions, and then we turn to their associated Lévy processes. We treat exponential Lévy stock models with an underlying bilateral Gamma pr…

We consider a setting in which the objective is to learn to navigate in a controlled Markov process (CMP) where transition probabilities may abruptly change. For this setting, we propose a performance measure called exploration steps which counts the time steps at which the learner lacks sufficient knowledge to navigat…

This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with many popular methods for estimating parameterized value functions. B…

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

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

New algorithm identifies best policy in MDPs faster.

The balance between exploration and exploitation is a key problem for reinforcement learning methods, especially for Q-learning. In this paper, a fidelity-based probabilistic Q-learning (FPQL) approach is presented to naturally solve this problem and applied for learning control of quantum systems. In this approach, fi…

Feature engineering is a crucial step in the process of predictive modeling. It involves the transformation of given feature space, typically using mathematical functions, with the objective of reducing the modeling error for a given target. However, there is no well-defined basis for performing effective feature engin…

SAMBA improves safe reinforcement learning with active exploration metrics.

ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.

Researchers study the geometric properties of a specific type of stable processes.

This paper analyzes the multi-armed bandit problem using frequency-domain methods.

Agent learns diverse hierarchical structures in unknown environments.

Estimates rewards from a demonstrator's learning process.

Proposes a method to accelerate safe sequential learning using offline data.