Results 261 to 270 of about 6,930,474 (290)
Eigenspace-based reinforcement learning acceleration of statistical convergence in turbulent flows.
Mach Learn ApplMasclans N, Jofre L.
europepmc +1 more source
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Relaxed Exploration Constrained Reinforcement Learning
International Joint Conference on Autonomous Agents and Multiagent Systems, 2023This research introduces a novel setting for reinforcement learning with constraints, termed Relaxed Exploration Constrained Reinforcement Learning (RECRL). Similar to standard constrained reinforcement learning (CRL), the objective in RECRL is to discover a policy that maximizes the environmental return while adhering to a predefined set of ...
Shahaf S. Shperberg +2 more
openaire +3 more sources
Learning to soar: Resource-constrained exploration in reinforcement learning
The International Journal of Robotics Research, 2014This paper examines temporal difference reinforcement learning with adaptive and directed exploration for resource-limited missions. The scenario considered is that of an unpowered aerial glider learning to perform energy-gaining flight trajectories in a thermal updraft.
Jen Jen Chung +2 more
openaire +4 more sources
Uniformly constrained reinforcement learning
Autonomous Agents and Multi-Agent Systems, 2023Jaeyoung Lee 0003 +2 more
openaire +1 more source
Entropy Seeking Constrained Multiagent Reinforcement Learning
International Joint Conference on Autonomous Agents and Multiagent SystemsMultiagent Reinforcement Learning (MARL) has been successfully applied to domains requiring close coordination among many agents. However, real-world tasks require safety specifications that are not generally considered by MARL algorithms. In this work, we introduce an Entropy Seeking Constrained (ESC) approach aiming to learn safe cooperative policies
Ayhan Alp Aydeniz +3 more
openaire +2 more sources