Erik M. Lintunen

Erik M. Lintunen, Nadia M. Ady, Christian Guckelsberger

Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated goal-conditioned RL: "Diversity Progress" (DP). The learner forms a curriculum based on observed improvement in discriminability over its set of goals. Our proposed method is applicable to the class of discriminability-motivated agents, where the intrinsic reward is computed as a function of the agent's certainty of following the true goal being pursued. This reward can motivate the agent to learn a set of diverse skills without extrinsic rewards. We demonstrate empirically that a DP-motivated agent can learn a set of distinguishable skills faster than previous approaches, and do so without suffering from a collapse of the goal distribution -- a known issue with some prior approaches. We end with plans to take this proof-of-concept forward.

Erik M. Lintunen

In self-supervised reinforcement learning (RL), one of the key challenges is learning a diverse set of skills to prepare agents for unknown future tasks. Despite impressive advances, scalability and evaluation remain prevalent issues. Regarding scalability, the search for meaningful skills can be obscured by high-dimensional feature spaces, where relevant features may vary across downstream task domains. For evaluating skill diversity, defining what constitutes "diversity" typically requires a hard commitment to a specific notion of what it means for skills to be diverse, potentially leading to inconsistencies in how skill diversity is understood, making results across different approaches hard to compare, and leaving many forms of diversity unexplored. To address these issues, we adopt a measure of sample diversity that translates ideas from ecology to machine learning -- the Vendi Score -- allowing the user to specify and evaluate any desired form of diversity. We demonstrate how this metric facilitates skill evaluation and introduce VendiRL, a unified framework for learning diversely diverse sets of skills. Given distinct similarity functions, VendiRL motivates distinct forms of diversity, which could support skill-diversity pretraining in new and richly interactive environments where optimising for various forms of diversity may be desirable.

Erik M. Lintunen, Nadia M. Ady, Sebastian Deterding et al.

Computational modelling offers a powerful tool for formalising psychological theories, making them more transparent, testable, and applicable in digital contexts. Yet, the question often remains: how should one computationally model a theory? We provide a demonstration of how formalisms taken from artificial intelligence can offer a fertile starting point. Specifically, we focus on the "need for competence", postulated as a key basic psychological need within Self-Determination Theory (SDT) -- arguably the most influential framework for intrinsic motivation (IM) in psychology. Recent research has identified multiple distinct facets of competence in key SDT texts: effectance, skill use, task performance, and capacity growth. We draw on the computational IM literature in reinforcement learning to suggest that different existing formalisms may be appropriate for modelling these different facets. Using these formalisms, we reveal underlying preconditions that SDT fails to make explicit, demonstrating how computational models can improve our understanding of IM. More generally, our work can support a cycle of theory development by inspiring new computational models, which can then be tested empirically to refine the theory. Thus, we provide a foundation for advancing competence-related theory in SDT and motivational psychology more broadly.