Related papers: Risk-Seeking versus Risk-Avoiding Investments in N…
Methods for learning optimal policies in autonomous agents often assume that the way the domain is conceptualised---its possible states and actions and their causal structure---is known in advance and does not change during learning. This…
In order to collaborate safely and efficiently, robots need to anticipate how their human partners will behave. Some of today's robots model humans as if they were also robots, and assume users are always optimal. Other robots account for…
In cybersecurity, attackers range from brash, unsophisticated script kiddies and cybercriminals to stealthy, patient advanced persistent threats. When modeling these attackers, we can observe that they demonstrate different risk-seeking and…
Autonomous systems can substantially enhance a human's efficiency and effectiveness in complex environments. Machines, however, are often unable to observe the preferences of the humans that they serve. Despite the fact that the human's and…
The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment. This is especially important in safety-critical…
In the study by Chen et al. (2023) [01], the large language model GPT demonstrated economic rationality comparable to or exceeding the average human level in tasks such as budget allocation and risk preference. Building on this finding,…
Automated decision-making tools increasingly assess individuals to determine if they qualify for high-stakes opportunities. A recent line of research investigates how strategic agents may respond to such scoring tools to receive favorable…
We introduce two tactics to attack agents trained by deep reinforcement learning algorithms using adversarial examples, namely the strategically-timed attack and the enchanting attack. In the strategically-timed attack, the adversary aims…
Forecasting corporate financial distress increasingly requires capturing firms' adoption of transformative technologies such as artificial intelligence, yet model performance remains vulnerable to temporal distribution shifts as these…
Maintaining the stability of the modern power grid is becoming increasingly difficult due to fluctuating power consumption, unstable power supply coming from renewable energies, and unpredictable accidents such as man-made and natural…
Guided policy search algorithms have been proven to work with incredible accuracy for not only controlling a complicated dynamical system, but also learning optimal policies from various unseen instances. One assumes true nature of the…
The objectives of option hedging/trading extend beyond mere protection against downside risks, with a desire to seek gains also driving agent's strategies. In this study, we showcase the potential of robust risk-aware reinforcement learning…
One typical assumption in inverse reinforcement learning (IRL) is that human experts act to optimize the expected utility of a stochastic cost with a fixed distribution. This assumption deviates from actual human behaviors under ambiguity.…
On markets with receding prices, artificial noise traders may consider alternatives to buy-and-hold. By simulating variations of the Parrondo strategy, using real data from the Swedish stock market, we produce first indications of a…
The long-term impact of algorithmic decision making is shaped by the dynamics between the deployed decision rule and individuals' response. Focusing on settings where each individual desires a positive classification---including many…
Rational agents are usually built to maximize rewards. However, AGI agents can find undesirable ways of maximizing any prior reward function. Therefore value learning is crucial for safe AGI. We assume that generalized states of the world…
Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many practical applications, however, interactions with the…
Robust planning in interactive scenarios requires predicting the uncertain future to make risk-aware decisions. Unfortunately, due to long-tail safety-critical events, the risk is often under-estimated by finite-sampling approximations of…
The goal of this research is to develop agents that are adaptive and predictable and timely. At first blush, these three requirements seem contradictory. For example, adaptation risks introducing undesirable side effects, thereby making…
Autonomous vehicles inevitably encounter a vast array of scenarios in real-world environments. Addressing long-tail scenarios, particularly those involving intensive interactions with numerous traffic participants, remains one of the most…