Novelty Producing Synaptic Plasticity
| Autor: | George H. L. Fletcher, Giovanni Iacca, Mykola Pechenizkiy, Decebal Constantin Mocanu, Anil Yaman |
|---|---|
| Přispěvatelé: | Data Mining, Process Science, Database Group, EAISI Health, EAISI Foundational |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Artificial neural network Property (programming) business.industry Computer science Process (engineering) Computer Science - Artificial Intelligence Novelty Computer Science - Neural and Evolutionary Computing Neuro-evolution Machine learning computer.software_genre Unsupervised learning Synaptic plasticity Artificial Intelligence (cs.AI) Neural and Evolutionary Computing (cs.NE) Artificial intelligence business Reinforcement computer |
| Zdroj: | GECCO Companion GECCO'20: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, 93-94 STARTPAGE=93;ENDPAGE=94;TITLE=GECCO'20: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion |
| Popis: | A learning process with the plasticity property often requires reinforcement signals to guide the process. However, in some tasks (e.g. maze-navigation), it is very difficult (or impossible) to measure the performance of an agent (i.e. a fitness value) to provide reinforcements since the position of the goal is not known. This requires finding the correct behavior among a vast number of possible behaviors without having the knowledge of the reinforcement signals. In these cases, an exhaustive search may be needed. However, this might not be feasible especially when optimizing artificial neural networks in continuous domains. In this work, we introduce novelty producing synaptic plasticity (NPSP), where we evolve synaptic plasticity rules to produce as many novel behaviors as possible to find the behavior that can solve the problem. We evaluate the NPSP on maze-navigation on deceptive maze environments that require complex actions and the achievement of subgoals to complete. Our results show that the search heuristic used with the proposed NPSP is indeed capable of producing much more novel behaviors in comparison with a random search taken as baseline. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|