In a recent blog post, Binance stated its support for the AI model ChatGPT, highlighting its potential to help improve cryptocurrency adoption and education. The chatbot developed by OpenAI went viral in a very short time, quickly becoming one of the fastest growing consumer apps in history. The cryptocurrency exchange platform Binance discussed the immense potential of generative AI, which seems to have taken the tech world by storm. Within the post, the exchange discussed the potential of AI to accelerate mainstream adoption of digital assets. Apparently, ChatGPT has been a consistent headline so far in 2023.

Theories of reinforcement learning in neuroscience have focused on two families of algorithms. Model-based algorithms achieve flexibility at computational expense, by rebuilding values from a model of the environment. We examine an intermediate class of algorithms, the successor representation (SR), which caches long-run state expectancies, blending model-free efficiency with model-based flexibility. Although previous reward revaluation studies distinguish model-free from model-based learning algorithms, such designs cannot discriminate between model-based and SR-based algorithms, both of which predict sensitivity to reward revaluation. However, changing the transition structure ('transition revaluation') should selectively impair revaluation for the SR.

As computational agents are increasingly used beyond research labs, their success will depend on their ability to learn new skills and adapt to their dynamic, complex environments. If human users — without programming skills — can transfer their task knowledge to the agents, learning rates can increase dramatically, reducing costly trials. The TAMER framework guides the design of agents whose behavior can be shaped through signals of approval and disapproval, a natural form of human feedback. Whereas early work on TAMER assumed that the agent's only feedback was from the human teacher, this paper considers the scenario of an agent within a Markov decision process (MDP), receiving and simultaneously learning from both MDP reward and human reinforcement signals. Preserving MDP reward as the determinant of optimal behavior, we test two methods of combining human reinforcement and MDP reward and analyze their respective performances. Both methods create a predictive model, H-hat, of human reinforcement and use that model in different ways to augment a reinforcement learning (RL) algorithm. We additionally introduce a technique for appropriately determining the magnitude of the model's influence on the RL algorithm throughout time and the state space.

As computational learning agents move into domains that incur real costs (e.g., autonomous driving or financial investment), it will be necessary to learn good policies without numerous high-cost learning trials. One promising approach to reducing sample complexity of learning a task is knowledge transfer from humans to agents. Ideally, methods of transfer should be accessible to anyone with task knowledge, regardless of that person's expertise in programming and AI. This thesis statement focuses on allowing a human trainer to interactively shape an agent's policy via reinforcement signals.