Novelty producing synaptic plasticity

Abstract

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.

Curriculum Learning for Robot Manipulation Tasks With Sparse Reward Through Environment Shifts

“…MCC was demonstrated for the very first time in a maze navigation problem [13]. Mazes are, in fact, a paradigmatic example of tasks with sparse, delayed reward [15], for which various approaches based on quality search [16], [17] or novelty [18] have been proposed. According to the setting proposed in [13], tasks (mazes) are co-evolved with agents (maze navigators) controlled by neural networks.…”