Alistair Letcher

reinforcement learning (2) stochastic gradient descent (1) policy optimization (1) function approximation (1) gradient descent (1) adversarial attack (1) optimization algorithm (1) generative adversarial network (1) differentiable game (1) algorithm discovery (1) potential game (1) loss surface (1) local optimum (1) symplectic gradient adjustment (1) hamiltonian game (1) stable fixed point (1) mirror learning (1) cheap talk (1) hessian eigenvector (1)