Applying reinforcement learning (RL) to combinatorial optimization problems is attractive as it removes the need for expert knowledge or pre-solved instances. However, it is unrealistic …
We introduce SCAL, an algorithm designed to perform efficient exploration-exploration in any unknown weakly-communicating Markov Decision Process (MDP) for which an upper …
Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or …
C Bodnar, B Day, P Lió - Proceedings of the AAAI Conference on Artificial …, 2020 - aaai.org
Reinforcement Learning (RL) has achieved impressive performance in many complex environments due to the integration with Deep Neural Networks (DNNs). At the same time …
Exploration is an essential component of reinforcement learning algorithms, where agents need to learn how to predict and control unknown and often stochastic environments …
H Qian, Y Yu - Frontiers of Computer Science, 2021 - Springer
Reinforcement learning is about learning agent models that make the best sequential decisions in unknown environments. In an unknown environment, the agent needs to …
X Zhang, Y Ma, A Singla - Advances in Neural Information …, 2020 - proceedings.neurips.cc
Efficient exploration is one of the main challenges in reinforcement learning (RL). Most existing sample-efficient algorithms assume the existence of a single reward function during …
Evolution strategies (ES) are a family of black-box optimization algorithms able to train deep neural networks roughly as well as Q-learning and policy gradient methods on challenging …
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical …