4.2 Symbolic Cognitive Architectures 59 sentational and computational power, in theory), in practice symbolic architectures tend to be weak in learning, creativity, procedure learning, and episodic and associative memory. Decades of work in this tradition have not resolved these issues, which has led many researchers to explore other options. A few of the more important symbolic cognitive architectures are: e SOAR [LRN87], a classic example of expert rule-based cognitive architecture designed to model general intelligence. It has recently been extended to handle sensorimotor functions, though in a somewhat cognitively unnatural way; and is not yet strong in areas such as episodic memory, creativity, handling uncertain knowledge, and reinforcement learning. e ACT-R [AL03] is fundamentally a symbolic system, but Duch classifies it as a hybrid sys- tem because it incorporates connectionist-style activation spreading in a significant role; and there is an experimental thoroughly connectionist implementation to complement the pri- mary mainly-symbolic implementation. Its combination of SOAR-style “production rules” with large-scale connectionist dynamics allows it to simulate a variety of human psycholog- ical phenomena, but abstract reasoning, creativity and transfer learning are still missing. e EPIC [RCKO]], a cognitive architecture aimed at capturing human perceptual, cognitive and motor activities through several interconnected processors working in parallel. The system is controlled by production rules for cognitive processors and a set of perceptual (visual, auditory, tactile) and motor processors operating on symbolically coded features rather than raw sensory data. It has been connected to SOAR for problem solving, planning and learning, e ICARUS [Lan05], an integrated cognitive architecture for physical agents, with knowledge specified in the form of reactive skills, each denoting goal-relevant reactions to a class of problems. The architecture inclides a n