Local policy search with Bayesian optimization

Abstract

Reinforcement learning (RL) aims to find an optimal policy by interaction with an environment. Consequently, learning complex behavior requires a vast number of samples, which can be prohibitive in practice. Nevertheless, instead of systematically reasoning and actively choosing informative samples, policy gradients for local search are often obtained from random perturbations. These random samples yield high variance estimates and hence are sub-optimal in terms of sample complexity. Actively selecting informative samples is at the core of Bayesian optimization, which constructs a probabilistic surrogate of the objective from past samples to reason about informative subsequent ones. In this paper, we propose to join both worlds. We develop an algorithm utilizing a probabilistic model of the objective function and its gradient. Based on the model, the algorithm decides where to query a noisy zeroth-order oracle to improve the gradient estimates. The resulting algorithm is a novel type of policy search method, which we compare to existing black-box algorithms. The comparison reveals improved sample complexity and reduced variance in extensive empirical evaluations on synthetic objectives. Further, we highlight the benefits of active sampling on popular RL benchmarks.

arXiv commentPresented at the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021

References in corpus (11)

• Continuous control with deep reinforcement learning
• Trust Region Policy Optimization
• BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization
• Max-value Entropy Search for Efficient Bayesian Optimization
• Scalable Global Optimization via Local Bayesian Optimization
• Bayesian Optimization with Gradients
• Bayesian Optimization with Adaptive Kernels for Robot Control
• Better Exploration with Optimistic Actor-Critic
• Guided evolutionary strategies: Augmenting random search with surrogate gradients
• Gait learning for soft microrobots controlled by light fields
• Optimization, fast and slow: optimally switching between local and Bayesian optimization

Cited by in corpus (3)

• On Controller Tuning with Time-Varying Bayesian Optimization
• Local Bayesian Optimization for Controller Tuning with Crash Constraints
• Simulation-Aided Policy Tuning for Black-Box Robot Learning