153 citations · 363 across the 29 of their papers we have counts for
3 papers · 2 filters
Target Entropy Annealing for Discrete Soft Actor-Critic
Yaosheng Xu, Dailin Hu, Litian Liang +3
Soft Actor-Critic (SAC) is considered the state-of-the-art algorithm in continuous action space settings. It uses the maximum entropy framework for efficiency and stability, and ap…
Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates
Litian Liang, Yaosheng Xu, Stephen McAleer +4
Temporal-Difference (TD) learning methods, such as Q-Learning, have proven effective at learning a policy to perform control tasks. One issue with methods like Q-Learning is that t…
Independent Natural Policy Gradient Always Converges in Markov Potential Games
Roy Fox, Stephen McAleer, Will Overman +1
Multi-agent reinforcement learning has been successfully applied to fully-cooperative and fully-competitive environments, but little is currently known about mixed cooperative/comp…