Search Results for author:
Found 6 papers, 1 papers with code
Three-Head Neural Network Architecture for AlphaZero Learning
A three-head network architecture has been recently proposed that can learn a third action-value head on a fixed dataset the same as for two-head net.
Mutex Graphs and Multicliques: Reducing Grounding Size for Planning
We present an approach to representing large sets of mutual exclusions, also known as mutexes or mutex constraints.
Domain-Independent Cost-Optimal Planning in ASP
Experiments to compare the two approaches with the only known cost-optimal planner in SAT reveal good potentials for stepless planning in ASP.
Adversarial Policy Gradient for Alternating Markov Games
As policy gradient method is a kind of generalized policy iteration, we show how these differences in policy iteration are reflected in policy gradient for AMGs.
Neurohex: A Deep Q-learning Hex Agent
DeepMind's recent spectacular success in using deep convolutional neural nets and machine learning to build superhuman level agents --- e. g. for Atari games via deep Q-learning and for the game of Go via Reinforcement Learning --- raises many questions, including to what extent these methods will succeed in other domains.
