Related papers: Hyperbolic Discounting and Learning over Multiple …
Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or complex multi-agent architectures often suffer from hallucination or computational…
There is a consensus that human and non-human subjects experience temporal distortions in many stages of their perceptual and decision-making systems. Similarly, intertemporal choice research has shown that decision-makers undervalue future…
Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a…
Present bias, the tendency to overvalue immediate rewards while undervaluing future ones, is a well-known barrier to achieving long-term goals. As artificial intelligence and behavioral economics increasingly focus on this phenomenon, the…
Despite a strong desire to quit, individuals with long-term substance use disorder (SUD) often struggle to resist drug use, even when aware of its harmful consequences. This disconnect between knowledge and compulsive behavior reflects a…
Sequential decision making in the presence of uncertainty and stochastic dynamics gives rise to distributions over state/action trajectories in reinforcement learning (RL) and optimal control problems. This observation has led to a variety…
Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, feature transformation remains essential for structured data,…
Market making (MM) is an important research topic in quantitative finance, the agent needs to continuously optimize ask and bid quotes to provide liquidity and make profits. The limit order book (LOB) contains information on all active…
Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…
Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture the desired behavior of a system, especially when dealing…
Reinforcement learning (RL) agents are commonly trained and evaluated in the same environment. In contrast, humans often train in a specialized environment before being evaluated, such as studying a book before taking an exam. The potential…
How can we design good goals for arbitrarily intelligent agents? Reinforcement learning (RL) is a natural approach. Unfortunately, RL does not work well for generally intelligent agents, as RL agents are incentivised to shortcut the reward…
In this thesis, we research learning algorithms for optimal decision making in two different contexts, Reinforcement Learning in Part I and Auction Design in Part II. Reinforcement learning (RL) is an area of machine learning that is…
We introduce an infinite-horizon, continuous-time portfolio selection problem faced by an agent with periodic S-shaped preference and present bias. The inclusion of a quasi-hyperbolic discount function leads to time-inconsistency and we…
Reward function, as an incentive representation that recognizes humans' agency and rationalizes humans' actions, is particularly appealing for modeling human behavior in human-robot interaction. Inverse Reinforcement Learning is an…
Specifying rewards for reinforcement learned (RL) agents is challenging. Preference-based RL (PbRL) mitigates these challenges by inferring a reward from feedback over sets of trajectories. However, the effectiveness of PbRL is limited by…
Systems for heating, ventilation and air-conditioning (HVAC) of buildings are traditionally controlled by a rule-based approach. In order to reduce the energy consumption and the environmental impact of HVAC systems more advanced control…
Increasing demand for algorithms that can learn quickly and efficiently has led to a surge of development within the field of artificial intelligence (AI). An important paradigm within AI is reinforcement learning (RL), where agents…
Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive,…
The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value across all states. While state-dependent discounting is…