Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
Augmenting Molecular Language Models with Local $n$-gram Memory
MolGram integrates a conditional n-gram memory module into molecular language models to address locality gaps in SMILES tokenization, improving performance on generation, forward prediction, and retrosynthesis while o...
-
Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
HSTU-based generative recommenders with 1.5 trillion parameters scale as a power law with compute up to GPT-3 scale, outperform baselines by up to 65.8% NDCG, run 5-15x faster than FlashAttention2 on long sequences, a...
-
Searching for Activation Functions
Automated search discovers Swish activation f(x) = x * sigmoid(βx) that improves top-1 ImageNet accuracy over ReLU by 0.9% on Mobile NASNet-A and 0.6% on Inception-ResNet-v2.
-
Don't Listen to Me: A Lightweight, Low-Latency Model for Own-Voice Cancellation in Far-Field Speech Enhancement
Introduces own-voice cancellation as a complement to target speaker extraction and benchmarks lightweight 2 ms latency models for far-field speech enhancement.
-
Overlap-aware segmentation for topological reconstruction of obscured objects
OASIS improves median intensity reconstruction error for low-energy electron tracks from -41.1% to -13.3% by weighting overlap regions in the training loss for the MIGDAL optical TPC.
-
Short window attention enables long-term memorization
Short sliding windows in hybrid attention-xLSTM models boost long-context performance by encouraging long-term memory use, and stochastic window sizing improves both short and long tasks.
-
Lyman-$\alpha$ forest constraints on pure and mixed fuzzy dark matter
Lyman-alpha forest data yield m_FDM > 1.9e-21 eV (95% CL) for pure FDM and f_FDM upper limits of 0.07-0.65 for mixed FDM at log10(m_FDM/eV) = -23 to -21.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.