State Specific Decision Making

State-specific decision-making focuses on developing algorithms and models that adapt decisions based on the current context or state of a system. Current research emphasizes leveraging deep learning architectures, such as transformers and neural networks, to efficiently represent and utilize state information for improved decision-making in diverse applications, including robotics, quantum computing, and natural language processing. This research is significant because it enables more robust and efficient solutions to complex problems across various scientific domains, improving the performance of autonomous systems and enhancing our understanding of complex systems.

Papers

May 15, 2022

RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states
Ziyuan Zhou, Guanjun Liu
Multi Agent Adversarial Perturbation Policy Gradient Multi Agent Deep Reinforcement Learning Actor Critic Reinforcement Learning State Specific Decision Making Mean Field Reinforcement Learning Adversarial Team Game

May 12, 2022

Accounting for the Sequential Nature of States to Learn Features for Reinforcement Learning
Nathan Michlo, Devon Jarvis, Richard Klein, Steven James
Reinforcement Learning Variational Autoencoders Feature Wise Metric Learning State Specific Decision Making Weak Supervision Signal

March 2, 2022

Flow-based density of states for complex actions
Jan M. Pawlowski, Julian M. Urban
Flow Based Field Theory State Specific Decision Making Human Action Phonon Density of State Flow Based Sampling

February 17, 2022

A novel HD Computing Algebra: Non-associative superposition of states creating sparse bundles representing order information
Stefan Reimann
Many Sparse Order Matter Sequential Information State Specific Decision Making Stochastic Noise Cognitive Computing Non Associativity

January 2, 2022

Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference
Hao Sun, Taiyi Wang
Reinforcement Learning Action Space State Specific Decision Making Temporal Action Abstraction

State Specific Decision Making

Papers

RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states

Accounting for the Sequential Nature of States to Learn Features for Reinforcement Learning

Flow-based density of states for complex actions

A novel HD Computing Algebra: Non-associative superposition of states creating sparse bundles representing order information

Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference