Related papers: SPRIG: Stackelberg Perception-Reinforcement Learni…
Reinforcement learning algorithms can acquire policies for complex tasks autonomously. However, the number of samples required to learn a diverse set of skills can be prohibitively large. While meta-reinforcement learning methods have…
As the pursuit of synergy between Artificial Intelligence (AI) and Operations Research (OR) gains momentum in handling complex inventory systems, a critical challenge persists: how to effectively reconcile AI's adaptive perception with OR's…
Understanding the agent's learning process, particularly the factors that contribute to its success or failure post-training, is crucial for comprehending the rationale behind the agent's decision-making process. Prior methods clarify the…
Deep reinforcement learning (DeepRL) agents surpass human-level performance in many tasks. However, the direct mapping from states to actions makes it hard to interpret the rationale behind the decision-making of the agents. In contrast to…
Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to prevent an RL agent from taking unsafe actions. However,…
Predictive power allocation is conceived for energy-efficient video streaming over mobile networks using deep reinforcement learning. The goal is to minimize the accumulated energy consumption of each base station over a complete video…
This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both…
Deep learning has revolutionized many areas of machine learning, from computer vision to natural language processing, but these high-performance models are generally "black box." Explaining such models would improve transparency and trust…
Long-horizon multimodal agents in open-world games must stay goal-directed across many low-level interactions under tight token and latency budgets. Existing approaches often trade off costly per-step reasoning against reactive execution…
Motivated by the question of how a principal can maximize its utility in repeated interactions with a learning agent, we study repeated games between an principal and an agent employing a mean-based learning algorithm. Prior work has shown…
We consider a setting for Inverse Reinforcement Learning (IRL) where the learner is extended with the ability to actively select multiple environments, observing an agent's behavior on each environment. We first demonstrate that if the…
An important goal in reinforcement learning is to create agents that can quickly adapt to new goals while avoiding situations that might cause damage to themselves or their environments. One way agents learn is through exploration…
Policy iteration (PI) is a recursive process of policy evaluation and improvement for solving an optimal decision-making/control problem, or in other words, a reinforcement learning (RL) problem. PI has also served as the fundamental for…
This paper presents a novel approach combining inductive logic programming with reinforcement learning to improve training performance and explainability. We exploit inductive learning of answer set programs from noisy examples to learn a…
Intelligent agents rely heavily on prior experience when learning a new task, yet most modern reinforcement learning (RL) approaches learn every task from scratch. One approach for leveraging prior knowledge is to transfer skills learned on…
We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language. While different methods have been developed to represent the environment information and language actions,…
This paper addresses the problem of training a reinforcement learning (RL) policy under partial observability by exploiting a privileged, anytime-feasible planner agent available exclusively during training. We formalize this as a Partially…
Human-aligned deep learning models exhibit behaviors consistent with human values, such as robustness, fairness, and honesty. Transferring these behavioral properties to models trained on different tasks or data distributions remains…
We study the incentivized information acquisition problem, where a principal hires an agent to gather information on her behalf. Such a problem is modeled as a Stackelberg game between the principal and the agent, where the principal…
Imitation learning in a high-dimensional environment is challenging. Most inverse reinforcement learning (IRL) methods fail to outperform the demonstrator in such a high-dimensional environment, e.g., Atari domain. To address this…