Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning

Abstract

In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning algorithm DQN achieved human-level performance in many Atari 2600 games. The purpose of this study is twofold. First, we propose two activation functions for neural network function approximation in reinforcement learning: the sigmoid-weighted linear unit (SiLU) and its derivative function (dSiLU). The activation of the SiLU is computed by the sigmoid function multiplied by its input. Second, we suggest that the more traditional approach of using on-policy learning with eligibility traces, instead of experience replay, and softmax action selection with simple annealing can be competitive with DQN, without the need for a separate target network. We validate our proposed approach by, first, achieving new state-of-the-art results in both stochastic SZ-Tetris and Tetris with a small 10$\times$10 board, using TD($\lambda$) learning and shallow dSiLU network agents, and, then, by outperforming DQN in the Atari 2600 domain by using a deep Sarsa($\lambda$) agent with SiLU and dSiLU hidden units.

18 pages, 22 figures; added deep RL results for SZ-Tetris

References in corpus (1)

• Massively Parallel Methods for Deep Reinforcement Learning

Cited by in corpus (11)

• Searching for Activation Functions
• On the Selection of Initialization and Activation Function for Deep Neural Networks
• One-loop matrix element emulation with factorisation awareness
• What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
• An unsupervised deep learning approach in solving partial integro-differential equations
• Weighted Sigmoid Gate Unit for an Activation Function of Deep Neural Network
• Online Meta-learning by Parallel Algorithm Competition
• Learning and Inference in Imaginary Noise Models
• Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts
• Goldilocks Neural Networks
• Unnormalized Variational Bayes