Tal Kachman

Research

My main research focus is on multiagent interaction, complex systems and reinforcement learning, with applications spanning from theoretical foundations to practical implementations.

Current Research Areas

Machine Learning & AI

  • Classical and deep Reinforcement learning
  • Multiagent systems
  • Diffusion based generative models
  • Algorithmic foundations of machine and deep learning

Complex Systems & Game Theory

  • Computational game theory
  • Complex systems analysis
  • Lyapunov exponents for diversity
  • Bifurcations in differentiable games

Quantum Computing

  • Quantum machine learning
  • Quantum space distance estimation
  • Quantum walk algorithms
  • Quantum topological classification

Recent Publications

Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members

Recent publication in multiagent systems

Lyapunov Exponents for Diversity in Differentiable Games

Research on game theory and dynamical systems

Using bifurcations for diversity in differentiable games

Theoretical work on complex system behavior

Patents

Quantum space distance estimation for classifier training

Patent in quantum machine learning applications

Quantum walk for community clique detection

Algorithm for network analysis using quantum computing

Quantum topological classification

Methods for quantum-enhanced classification

Previous Research (Physics Background)

  • Non-equilibrium statistical mechanics
  • Foundations of quantum mechanics
  • Quantum chaos
  • Molecular dynamics and computational chemistry
  • Nonlinear optics
  • Heat conduction in nanometric systems