1. Munchausen Reinforcement Learning;vieillard,2020
2. Parameterized MDPs and Reinforcement Learning Problems--A Maximum Entropy Principle-Based Framework
3. Deep Exploration via Bootstrapped DQN;osband;Advances in neural information processing systems,2016
4. Adam: A Method for Stochastic Optimization;kingma,2015
5. On the Impact of the Activation Function on Deep Neural Networks Training;hayou;Proc ICML,2019