Wah Loon KengSoft Actor-Critic for continuous and discrete actionsWith the Atari benchmark complete for all the core RL algorithms in SLM Lab, I finally had time to implement a new algorithm, Soft…Aug 11, 20194Aug 11, 20194
Wah Loon KengMulti-inheritance magic in SLM LabDeep RL is known to be complex in terms of engineering, because it involves so many things. One goal of SLM Lab is to reduce this…Sep 26, 20181Sep 26, 20181
Wah Loon Kengpip module for RL agents in SLM LabAs part of the usability improvement in SLM Lab v2.0.0, we have also made it possible to just use the agents outside of the SLM framework…Sep 5, 2018Sep 5, 2018
Wah Loon KengDeep Reinforcement Learning with SLM LabSLM-Lab v2.0.0 was recently released. This version represents a major milestone, as it has grown to over a dozen algorithms while retaining…Sep 5, 2018Sep 5, 2018
Wah Loon KengOpenAI Five DotA: Solving the Global Skill ProblemLaura and I were talking about how we would solve the global skill problem in OpenAI’s DotA Five, which is still evidently lacking from…Aug 13, 20181Aug 13, 20181
Wah Loon KengSemantic correspondence via PowerNet expansionstart with cartpole network, 4 inputs, 2 outputs, train networkAug 9, 2018Aug 9, 2018
Wah Loon KengOpenAI Five DotA: Next ChallengesIf you don’t already know, OpenAI’s Dota Five had just played against some pro players during the benchmark event. It was streamed on…Aug 7, 20181Aug 7, 20181
Wah Loon KengFalsifiability and General Turing TestAnother continued note to my coauthor.Jul 24, 2018Jul 24, 2018
Wah Loon KengStages of Semantics GroundingThis is a correspondence to my coauthor.Jul 19, 2018Jul 19, 2018