We argue that cognitive models can provide a common ground between human users and deep reinforcement learning (Deep RL) algorithms for purposes of explainable artificial intelligence (AI). Casting both the human and learner as cognitive models provides common mechanisms to compare and understand their underlying decision-making processes. This common grounding allows us to identify divergences and explain the learner's behavior in human understandable terms. We present novel salience techniques that highlight the most relevant features in each model's decision-making, as (...) well as examples of this technique in common training environments such as Starcraft II and an OpenAI gridworld. (shrink)

There is an apparent connection between reinforcement learning and agency. Artificial entities controlled by reinforcement learning algorithms are standardly referred to as agents, and the mainstream view in the psychology and neuroscience of agency is that humans and other animals are reinforcement learners. This article examines this connection, focusing on artificial reinforcement learning systems and assuming that there are various forms of agency. Artificial reinforcement learning systems satisfy plausible conditions for minimal agency, and those (...) which use models of the environment to perform forward search are capable of a form of agency which may reasonably be called action for reasons. (shrink)

Psychology is in a preparadigmatic or pre-unified stage of scientific development. Two characteristics of psychology's status are: lack of cumulative scientific growth and experimental-theoretical overgeneralization. The reinforcer, as a construct in theories and as a critical element of behavioral change, has been a casualty of the separatism between such factions as radical behaviorism and cognitive psychology. In the end, psychology as a progressive science has been impeded, and psychological practitioners have been left to use intervention techniques (...) that are not the most effective or efficient. In order to improve upon this situation, unification is needed between radical behaviorism and cognitive psychology, among other disciplines. However, the issue of the reinforcer is only one of many areas where such unification should be pursued and attained. 2012 APA, all rights reserved). (shrink)

Identity politics has been critiqued in various ways. One central problem—the Reinforcement Problem—claims that identity politics reinforces groups rooted in oppression thereby undermining its own liberatory aims. Here I consider two versions of the problem—one psychological and one metaphysical. I defang the first by drawing on work in social psychology. I then argue that careful consideration of the metaphysics of social groups and of the practice of identity politics provides resources to dissolve the second version. Identity politics involves (...) the creation or transformation of groups in ways that do not succumb to the metaphysical Reinforcement Problem. (shrink)

Shared intention normally leads to joint action. It does this, it is commonly said, only because it is a characteristically stable phenomenon, a phenomenon that tends to persist from the time it is formed until the time it is fulfilled. However, the issue of what the stability of shared intention comes down to remains largely undertheorized. My aim in this paper is to remedy this shortcoming. I argue that shared intention is a source of moral and epistemic reasons, that responsiveness (...) to such reasons on the part of each individual reinforces her own relevant attitudes, and that this enhances the stability of the shared intention as a whole. We thus discover an important self-reinforcing and stability-enhancing mechanism at the heart of shared intention and action. It follows from this proposal that the psychological commitment that an individual exhibits in joint action is normally a function not only of her own participatory intention, as often maintained, but also of her endorsement of the reasons created by her group’s shared intention to so act. (shrink)

Teachers perform the duty of imparting knowledge and educating people, and undertake the important task of cultivating socialism builders and successors and the mission to improve the quality of the nation a whole. Therefore, teachers should set an example in abiding by teachers’ professional ethics, intensifying construction of teachers’ morality, and improving level of education. This article proposes the constructive thought in teachers’ morality construction in vocational education, that is, to try to improve the overall quality of a teacher in (...) vocational education. Improvement of moral trait is the foundation, improvement of cultural awareness the key, improvement of innovative quality the core, and improvement of health and psychological quality is the basis. (shrink)

The doctrine of double effect is a moral principle that distinguishes between harm we cause as a means to an end and harm that we cause as a side-effect. As a purely descriptive matter, the DDE is well established that it describes a consistent feature of human moral judgment. There are, however, several rival theories of its psychological cause. I review these theories and consider their advantages and disadvantages. Critically, most extant psychological theories of the DDE regard it as an (...) accidental byproduct of cognitive architecture. This may provide philosophers with some reason to question its normative significance. (shrink)