Search Results for author:
Found 2 papers, 1 papers with code
Self-Guided Evolution Strategies with Historical Estimated Gradients
Evolution Strategies (ES) are a class of black-box optimization algorithms and have been widely applied to solve problems, e. g., in reinforcement learning (RL), where the true gradient is unavailable.
Deep exploration by novelty-pursuit with maximum state entropy
Efficient exploration is essential to reinforcement learning in huge state space.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
