MarI/O - Machine Learning for Video Games
SethBlingYouTube ↗
Further reading 5
Can a network evolve its own wiring? →First follow activations through a fixed network. In MarI/O, selection changes the connections themselves. Following a signal and searching for a useful topology are different operations.Reward and fitness both give feedback. What changes? →In reinforcement learning, rewards inform action choices. MarI/O uses a fitness score to select entire networks across generations.A better network or a longer look ahead? →Evolving a network changes its structure. Looking farther ahead changes how an agent evaluates future moves. Each addresses a different limitation.How do game agents improve beyond their starting point? →AlphaGo imitates games and then plays against itself. MarI/O selects and reproduces networks according to game progress.What cannot be recovered from the current observation? →Ask which distinctions the input representation discards. Earlier observations, feedback or prior knowledge may change what can be inferred.
Caption notes
MarI/O evolves networks with NEAT, rewarding progress through a Mario level. Selection and mutation produce increasingly effective controller actions.
Original passages · 5
The white squares stand for blocks the player can stand onOnly the neural networks that produce the highest fitness are selected to be bredbuild up neural networks from barebones without presupposing the best structureOnly the neural networks that produce the highest fitness are selectedwithout presupposing the best structure for the neurons and their connections