Two Soar studies
نویسندگان
چکیده
منابع مشابه
Cognitive Architectures as Lakatosian Research Programs: Two Case Studies
Cognitive architectures—task-general theories of the structure and function of the complete cognitive system—are sometimes argued to be more akin to frameworks or belief systems than scientific theories. The argument stems from the apparent non-falsifiability of existing cognitive architectures. Newell was aware of this criticism and argued that architectures should be viewed not as theories su...
متن کاملCognitive Architectures as Lakatosian Research Programmes: Two Case Studies
Cognitive architectures—task-general theories of the structure and function of the complete cognitive system—are sometimes argued to be more akin to frameworks or belief systems than scientific theories. The argument stems from the apparent non-falsifiability of existing cognitive architectures. Newell (1990) was aware of this criticism and argued that architectures should be viewed not as theo...
متن کاملSoar-RL: integrating reinforcement learning with Soar
In this paper, we describe an architectural modification to Soar that gives a Soar agent the opportunity to learn statistical information about the past success of its actions and utilize this information when selecting an operator. This mechanism serves the same purpose as production utilities in ACT-R, but the implementation is more directly tied to the standard definition of the reinforcemen...
متن کاملStrategies for Affect-Controlled Action-Selection in Soar-RL
Reinforcement learning (RL) agents can benefit from adaptive exploration/exploitation behavior, especially in dynamic environments. We focus on regulating this exploration/exploitation behavior by controlling the action-selection mechanism of RL. Inspired by psychological studies which show that affect influences human decision making, we use artificial affect to influence an agent’s action-sel...
متن کاملIntegrating Reinforcement Learning with Soar
In this paper, we describe an architectural modification to Soar that gives a Soar agent the opportunity to learn statistical information about the past success of its actions and utilize this information when selecting an operator. This mechanism serves the same purpose as production utilities in ACT-R, but the implementation is more directly tied to the standard definition of the reinforcemen...
متن کامل