Related papers: Predictive Information Accelerates Learning in RL
We address the problem of safe reinforcement learning from pixel observations. Inherent challenges in such settings are (1) a trade-off between reward optimization and adhering to safety constraints, (2) partial observability, and (3)…
Everything else being equal, simpler models should be preferred over more complex ones. In reinforcement learning (RL), simplicity is typically quantified on an action-by-action basis -- but this timescale ignores temporal regularities,…
In this work we introduce Salient Information Preserving Adversarial Training (SIP-AT), an intuitive method for relieving the robustness-accuracy trade-off incurred by traditional adversarial training. SIP-AT uses salient image regions to…
Soft Actor-Critic (SAC) is an off-policy actor-critic reinforcement learning algorithm, essentially based on entropy regularization. SAC trains a policy by maximizing the trade-off between expected return and entropy (randomness in the…
Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic account of this inconsistency: synthetic data improves a model only when the…
Traditionally, reinforcement learning (RL) agents learn to solve new tasks by updating their neural network parameters through interactions with the task environment. However, recent works demonstrate that some RL agents, after certain…
Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two…
In many predictive decision-making scenarios, such as credit scoring and academic testing, a decision-maker must construct a model that accounts for agents' propensity to "game" the decision rule by changing their features so as to receive…
Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior…
Climate change poses an existential threat, necessitating effective climate policies to enact impactful change. Decisions in this domain are incredibly complex, involving conflicting entities and evidence. In the last decades, policymakers…
Predictive Coding (PC) is an influential account of cortical learning. Much of recent work has focused on comparing PC to Backpropagation (BP) to find whether PC offers any advantages. Small scale experiments show that PC enables learning…
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…
Science consists on conceiving hypotheses, confronting them with empirical evidence, and keeping only hypotheses which have not yet been falsified. Under deductive reasoning they are conceived in view of a theory and confronted with…
Integrated sensing and communication (ISAC) technology is essential for supporting vehicular networks. However, the communication channel in this scenario exhibits time variations, and the potential targets may move rapidly, resulting in…
Children learn to build a visual representation of the world from unsupervised exploration and we hypothesize that a key part of this learning ability is the use of self-generated navigational information as a similarity label to drive a…
We propose a new framework for reasoning about information in complex systems. Our foundation is based on a variational extension of Shannon's information theory that takes into account the modeling power and computational constraints of…
Work in cognitive science and artificial intelligence has suggested that exposing learning agents to traces of interaction between multiple individuals can improve performance in a variety of settings, yet it remains unknown which features…
The interest in using reinforcement learning (RL) controllers in safety-critical applications such as robot navigation around pedestrians motivates the development of additional safety mechanisms. Running RL-enabled systems among uncertain…
Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution. A previous theoretical study has argued that this remarkable performance is because the meta-training protocol…
Interactive recommendation is able to learn from the interactive processes between users and systems to confront the dynamic interests of users. Recent advances have convinced that the ability of reinforcement learning to handle the dynamic…