Related papers: Data-Driven Knowledge Transfer in Batch $Q^*$ Lear…
Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naive formulations often degrade performance and in particular, identifying the tasks that would benefit from…
Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all…
Multi-task reinforcement learning (MTRL) aims to learn several tasks simultaneously for better sample efficiency than learning them separately. Traditional methods achieve this by sharing parameters or relabeled data between tasks. In this…
Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectively boost training…
Is more data always better to train vision-and-language models? We study knowledge transferability in multi-modal tasks. The current tendency in machine learning is to assume that by joining multiple datasets from different tasks their…
General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…
Diffusion models excel at sampling from complex, unnormalized distributions. In this work, we extend Maximum Entropy Reinforcement Learning (ME-RL) to diffusion processes, enabling sampling from the optimal policy trajectory distribution.…
Dynamic pricing strategies are crucial for firms to maximize revenue by adjusting prices based on market conditions and customer characteristics. However, designing optimal pricing strategies becomes challenging when historical data are…
In these notes we will tackle the problem of finding optimal policies for Markov decision processes (MDPs) which are not fully known to us. Our intention is to slowly transition from an offline setting to an online (learning) setting.…
In this paper, for POMDPs, we provide the convergence of a Q learning algorithm for control policies using a finite history of past observations and control actions, and, consequentially, we establish near optimality of such limit Q…
Recent progress in Learning by Reading and Machine Reading systems has significantly increased the capacity of knowledge-based systems to learn new facts. In this work, we discuss the problem of selecting a set of learning requests for…
In this paper, for Markov decision processes (MDPs) with unbounded state spaces we present refined upper bounds presented in [Kara et. al. JMLR'23] on finite model approximation errors via optimizing the quantizers used for finite model…
Knowledge Distillation (KD) transfers knowledge from large models to small models and has recently achieved remarkable success. However, the reliability of existing KD methods in real-world applications, especially under distribution shift,…
Scheduling problems are often tackled independently, and rarely solved by leveraging the commonalities across problems. Lack of awareness of this inter-task similarity could impede the search efficacy. A quantifiable relationship between…
We study the problem of representational transfer in RL, where an agent first pretrains in a number of source tasks to discover a shared representation, which is subsequently used to learn a good policy in a \emph{target task}. We propose a…
Multitask learning assumes that models capable of learning from multiple tasks can achieve better quality and efficiency via knowledge transfer, a key feature of human learning. Though, state of the art ML models rely on high customization…
Optimal control in non-stationary Markov decision processes (MDP) is a challenging problem. The aim in such a control problem is to maximize the long-term discounted reward when the transition dynamics or the reward function can change over…
Reinforcement learning (RL) tasks are typically framed as Markov Decision Processes (MDPs), assuming that decisions are made at fixed time intervals. However, many applications of great importance, including healthcare, do not satisfy this…
Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically…
Here, we explore the problem of error propagation mitigation in modular digital twins as a sequential decision process. Building on a companion study that used a Hidden Markov Model (HMM) to infer latent error regimes from surrogate-physics…