25 papers · ranked by Valyu relevance
Ao Feng, Yuyang Xie, Yankang Sun, Xuanzhi Wang + 3 more
'Jian Xiao' 'Srikanth Saripalli'] Autonomous exploration and mapping in unknown environments is a critical capability for robots. Existing exploration techniques (e.g., heuristic-based and learning-based methods) do not consider the regional legacy issues, i.e., the great impact of smaller unexplored regions on the…
Ali El Romeh, Seyedali Mirjalili
This work introduces the Advanced Multi-Objective Salp Swarm Algorithm Exploration Technique (AMET), which is a novel optimization framework designed to enhance the efficiency and robustness of multi-robot exploration. AMET combines the deterministic structure of Coordinated Multi-Robot Exploration (CME) with the…
Chunyang Liu, Dingfa Zhang, Weitao Liu, Xin Sui + 4 more
'Xiqiang Ma' 'Xiaokang Yang' 'Xiao Wang'] Autonomous exploration and mapping in unknown environments remain pivotal in robotics research. The efficiency of autonomous exploration is often constrained by irrational exploration strategies and incomplete map exploration. This paper proposes an efficient autonomous…
Manousos Linardakis, Iraklis Varlamis, Georgios Th. Papadopoulos
In the field of modern robotics, robots are proving to be useful in tackling high-risk situations, such as navigating hazardous environments like burning buildings, earthquake-stricken areas, or patrolling crime-ridden streets, as well as exploring uncharted caves. These scenarios share similarities with maze…
Arnav Jain, Lucas Lehnert, Irina Rish, Glen Berseth
Animals have a developed ability to explore that aids them in important tasks such as locating food, exploring for shelter, and finding misplaced items. These exploration skills necessarily track where they have been so that they can plan for finding items with relative efficiency. Contemporary exploration algorithms…
Jose Segovia-Martin, Felix Creutzig, James Winters
Higher levels of economic activity are often accompanied by higher energy use and consumption of natural resources. As fossil fuels still account for 80% of the global energy mix, energy consumption remains closely linked to greenhouse gas (GHG) emissions and thus to climate change. Under the assumption of sufficiently…
Erik J Peterson, Timothy D Verstynen
The optimal decision to exploit existing rewards, or explore looking for larger rewards, is known to be a mathematically intractable problem. Here we challenge this fundamental result in the learning and decision sciences by showing that there is an optimal solution if exploitation and exploration are treated as…
Liangpeng Zhang, Ke Tang, Xin Yao
Exploration has been a crucial part of reinforcement learning, yet several important questions concerning exploration efficiency are still not answered satisfactorily by existing analytical frameworks. These questions include exploration parameter setting, situation analysis, and hardness of MDPs, all of which are…
Valentin Baumann, Johannes Dambacher, Marit F. L. Ruitenberg, Judith Schomaker + 1 more
'Judith Schomaker' 'Kerstin Krauel'] Spatial exploration is a complex behavior that can be used to gain information about developmental processes, personality traits, or mental disorders. Typically, this is done by analyzing movement throughout an unknown environment. However, in human research, until now there has…
Ketika Garg, Christopher T. Kello, Paul E. Smaldino
Search requires balancing exploring for more options and exploiting the ones previously found. Individuals foraging in a group face another trade-off: whether to engage in social learning to exploit the solutions found by others or to solitarily search for unexplored solutions. Social learning can better exploit…
Ketika Garg, Paul E. Smaldino, Christopher T. Kello
Evolutionary theories of foraging hypothesize that foraging strategies evolve to maximize search efficiency. Many studies have investigated the central trade-off between explore-exploit and how individual foragers manage it under various conditions. For foragers in groups, this trade-off can be affected by the social…
M Dubois, J Habicht, J Michely, R Moran + 2 more
An exploration-exploitation trade-off, the arbitration between sampling a lesser-known against a known rich option, is thought to be solved using computationally demanding exploration algorithms. Given known limitations in human cognitive resources, we hypothesised the presence of additional cheaper strategies. We…
Jan Leike
We introduce exploration potential, a quantity that measures how much a reinforcement learning agent has explored its environment class. In contrast to information gain, exploration potential takes the problem's reward structure into account. This leads to an exploration criterion that is both necessary and sufficient…
Aryan Deshwal, Cory Simon, Janardhan Rao Doppa
Given a gas storage or separation task, we wish to search a library of nanoporous materials (NPMs) for the one with the optimal adsorption property. The high cost of measuring the adsorption property of an NPM, whether in the lab or a simulation, precludes exhaustive search. We explain, demonstrate, and advocate…
Vladimir V. Palyulin, Aleksei V. Chechkin, Rainer Klages, Ralf Metzler
'Ralf Metzler'] † Physics Department, Technical University of Munich, D-85747 Garching, Germany ‡ Akhiezer Institute for Theoretical Physics NSC KIPT, Kharkov, 61108, Ukraine ¶ Max-Planck-Institut f¨ur Physik komplexer Systeme, D-01187 Dresden, Germany § Department of Physics & Astronomy, University of Padova, 35122…
Miruna Pîslar, David Szepesvari, Georg Ostrovski, Diana Borsa + 1 more
'Tom Schaul'] Exploration remains a central challenge for reinforcement learning (RL). Virtually all existing methods share the feature of a monolithic behaviour policy that changes only gradually (at best). In contrast, the exploratory behaviours of animals and humans exhibit a rich diversity, namely including forms…
Authors not listed
Computer-Assisted Synthesis Programs are increasingly employed by organic chemists. Often, these tools combine neural networks for policy prediction with heuristic search algorithms. We propose two novel enhancements, which we call eUCT and dUCT, to the Monte Carlo tree search (MCTS) algorithm. The enhancements were…
Teodor Mihai Moldovan, Pieter Abbeel
In environments with uncertain dynamics exploration is necessary to learn how to perform well. Existing reinforcement learning algorithms provide strong exploration guarantees, but they tend to rely on an ergodicity assumption. The essence of ergodicity is that any state is eventually reachable from any other state by…
Kyanoush Seyed Yahosseini, Mehdi Moussaïd
Humans commonly engage in a variety of search behaviours, for example when looking for an object, a partner, information, or a solution to a complex problem. The success or failure of a search strategy crucially depends on the structure of the environment and the constraints it imposes on the individuals. Here we focus…
Authors not listed
Incorporating prior domain knowledge into Bayesian optimization (BO) remains difficult for statistical methods, which also typically suffer from limited interpretability. Large language models (LLMs) offer complementary strengths in reasoning and knowledge integration, but it remains unclear when and how they improve…
Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Alaa Saade, Shantanu Thakoor + 6 more
'Shantanu Thakoor' 'Bilal Piot' 'Bernardo Ávila Pires' 'Michal Vaľko' 'Thomas Mesnard' 'Tor Lattimore' 'Rémi Munos'] Exploration is essential for solving complex Reinforcement Learning (RL) tasks. Maximum State-Visitation Entropy (MSVE) formulates the exploration problem as a welldefined policy optimization problem…
Felix Kaspar
The term efficient has gained great popularity in the chemical literature, despite the lack of an applicable and relatable definition. In this perspective, a chemical definition of efficiency is discussed building on the concept of non-wasteful resource usage. It is proposed than an efficient method, synthesis or…
Yifan Wu, Aron Walsh, Alex Ganose
What is the minimum number of experiments, or calculations, required to find an optimal solution? Relevant chemical problems range from identifying a compound with target functionality within a given phase space to controlling materials synthesis and device fabrication conditions. A common feature in this application…
Sterling Baird, Jason R. Hall, Taylor D. Sparks
Would you rather search for a line inside a cube or a point inside a square? Physics-based simulations and wet-lab experiments often have symmetries (degeneracies) that allow reducing problem dimensionality or search space, but constraining these degeneracies is often unsupported or difficult to implement in many…
Authors not listed
Continuous manufacturing processes offer significant advantages over batch processes, including easier scalability, reduced costs, lower raw material and solvent consumption, and improved energy efficiency. A robust techno-economic assessment is therefore essential to evaluate and facilitate the adoption of such…