Learning to grow: Control of material self-assembly using evolutionary reinforcement learning
S Whitelam, I Tamblyn - Physical Review E, 2020 - APS
We show that neural networks trained by evolutionary reinforcement learning can enact
efficient molecular self-assembly protocols. Presented with molecular simulation trajectories …
efficient molecular self-assembly protocols. Presented with molecular simulation trajectories …
Evolutionary reinforcement learning of dynamical large deviations
S Whitelam, D Jacobson, I Tamblyn - The Journal of chemical physics, 2020 - pubs.aip.org
We show how to bound and calculate the likelihood of dynamical large deviations using
evolutionary reinforcement learning. An agent, a stochastic model, propagates a continuous …
evolutionary reinforcement learning. An agent, a stochastic model, propagates a continuous …
Adaptable automation with modular deep reinforcement learning and policy transfer
Z Raziei, M Moghaddam - Engineering Applications of Artificial Intelligence, 2021 - Elsevier
Future industrial automation systems are anticipated to be shaped by intelligent
technologies that allow for the adaptability of machines to the variations and uncertainties in …
technologies that allow for the adaptability of machines to the variations and uncertainties in …
Time series segmentation for state-model generation of autonomous aquatic drones: A systematic framework
Autonomous surface vessels are becoming increasingly important for water monitoring.
Their aim is to navigate rivers and lakes with limited intervention of human operators, to …
Their aim is to navigate rivers and lakes with limited intervention of human operators, to …
Combining experience replay with exploration by random network distillation
F Sovrano - 2019 IEEE conference on games (CoG), 2019 - ieeexplore.ieee.org
Our work is a simple extension of the paper" Exploration by Random Network Distillation"[1].
More in detail, we show how to efficiently combine Intrinsic Rewards with Experience Replay …
More in detail, we show how to efficiently combine Intrinsic Rewards with Experience Replay …
Crawling in Rogue's Dungeons With Deep Reinforcement Techniques
A Asperti, D Cortesi, C De Pieri… - IEEE Transactions …, 2019 - ieeexplore.ieee.org
This paper is a report of our extensive experimentation, during the last two years, of deep
reinforcement techniques for training an agent to move in the dungeons of the famous …
reinforcement techniques for training an agent to move in the dungeons of the famous …
Microracer: a didactic environment for deep reinforcement learning
A Asperti, M Del Brutto - … on Machine Learning, Optimization, and Data …, 2022 - Springer
MicroRacer is a simple, open source environment inspired by car racing especially meant
for the didactics of Deep Reinforcement Learning. The complexity of the environment has …
for the didactics of Deep Reinforcement Learning. The complexity of the environment has …
Inventory Management with Attention-Based Meta Actions
K Izumiya, E Simo-Serra - 2021 IEEE Conference on Games …, 2021 - ieeexplore.ieee.org
Roguelike games are a challenging environment for Reinforcement Learning (RL)
algorithms due to having to restart the game from the beginning when losing, randomized …
algorithms due to having to restart the game from the beginning when losing, randomized …
[PDF][PDF] MicroRacer: development of a didactic environment for deep reinforcement learning
M Del Brutto - amslaurea.unibo.it
Reinforcement Learning (RL) is a branch of machine learning where an agent taking actions
in a given environment is supposed to learn an optimal behaviour by acquiring experience …
in a given environment is supposed to learn an optimal behaviour by acquiring experience …
[PDF][PDF] Structured Multimodal Reinforcement Learning for Playing NetHack
K Izumiya - 2023 - waseda.repo.nii.ac.jp
Designing autonomous agents that play video games is important and valuable for game
design, balancing, and testing. Video games are also preferable benchmark environments …
design, balancing, and testing. Video games are also preferable benchmark environments …