Google
Ąż
AllImagesBooksNews Maps Videos Shopping
Search tools

Prioritized experience replay based on dynamics priority

Nature
Experience replay has been instrumental in achieving significant advancements in reinforcement learning by increasing the utilization of...
8 months ago

Reinforcement Learning: Deep Q-Networks

Towards Data Science
Teaching a shuttle to land on the moon using Deep Q-Networks in Python: A mathematical deep dive into Reinforcement Learning.
6 months ago

Large language models empowered agent-based modeling and simulation: a survey and perspectives

Nature
Agent-based modeling and simulation have evolved as a powerful tool for modeling complex systems, offering insights into emergent behaviors...
2 months ago

Eureka! NVIDIA Research Breakthrough Puts New Spin on Robot Learning

NVIDIA Blog
A new AI agent developed by NVIDIA Research that can teach robots complex skills has trained a robotic hand to perform rapid pen-spinning tricks.
13 months ago

Deep Reinforcement Learning Based Trajectory Planning Under Uncertain Constraints

Frontiers
In this article, we present state-of-the-art DRL-based collision-avoidance trajectory planning for uncertain environments such as a safe human coexistent...
31 months ago

Model-Based and Model-Free Replay Mechanisms for Reinforcement Learning in Neurorobotics

Frontiers
Experience replay is widely used in AI to bootstrap reinforcement learning (RL) by enabling an agent to remember and reuse past experiences.
29 months ago

Intrinsic fluctuations of reinforcement learning promote cooperation

Nature
In this work, we ask for and answer what makes classical temporal-difference reinforcement learning with $$\epsilon$$ -greedy strategies...
22 months ago

Accounting for multiscale processing in adaptive real-world decision-making via the hippocampus

Frontiers
For adaptive real-time behavior in real-world contexts, the brain needs to allow past information over multiple timescales to influence current processing...
9 months ago

Segregation dynamics with reinforcement learning and agent based modeling

Nature
In this paper, we combine Reinforcement Learning (RL) with Agent Based Modeling (ABM) in order to address the self-organizing dynamics of social segregation.
52 months ago

Multi-level deep Q-networks for Bitcoin trading strategies

Nature
The Bitcoin market has experienced unprecedented growth, attracting financial traders seeking to capitalize on its potential.
10 months ago