Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes
arXiv:1905.12667
Abstract
We propose a new class of structured methods for Monte Carlo (MC) sampling, called DPPMC, designed for high-dimensional nonisotropic distributions where samples are correlated to reduce the variance of the estimator via determinantal point processes. We successfully apply DPPMCs to problems involving nonisotropic distributions arising in guided evolution strategy (GES) methods for RL, CMA-ES techniques and trust region algorithms for blackbox optimization, improving state-of-the-art in all these settings. In particular, we show that DPPMCs drastically improve exploration profiles of the existing evolution strategy algorithms. We further confirm our results, analyzing random feature map estimators for Gaussian mixture kernels. We provide theoretical justification of our empirical results, showing a connection between DPPMCs and structured orthogonal MC methods for isotropic distributions.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- The NumPy array: a structure for efficient numerical computation
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Benchmarking Deep Reinforcement Learning for Continuous Control
- Determinantal point processes for machine learning
- Simple random search provides a competitive approach to reinforcement learning
- Orthogonal Random Features
- Structured Evolution with Compact Architectures for Scalable Policy Optimization
- The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings
- Efficient Sampling for k-Determinantal Point Processes
- Guided evolutionary strategies: Augmenting random search with surrogate gradients
- Generalized Spectral Kernels
- Provably Robust Blackbox Optimization for Reinforcement Learning