A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
This study proposes hidden state curiosity to enhance RL models' resilience against noise.
Curious hierarchical reinforcement learning improves learning performance.
Curiosity enhanced by audio-visual associations improves learning efficiency.
Meta-learning curiosity algorithms improves exploration across various tasks.
Robots learn actions and language through curiosity-driven self-exploration.
Reinforcement Learning enables to train an agent via interaction with the environment. However, in the majority of real-world scenarios, the extrinsic feedback is sparse or not sufficient, thus intrinsic reward formulations are needed to successfully train the agent. This work investigates and extends the paradigm of c…
Curiosity-Critic improves world model training by focusing on cumulative prediction error.
Curiosity-driven exploration using Bayesian surprise in latent space.
Quriosity analyzes curiosity-driven questions from diverse sources.
Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrins…
The design of recommendations strategies in the adaptive learning system focuses on utilizing currently available information to provide individual-specific learning instructions for learners. As a critical motivate for human behaviors, curiosity is essentially the drive to explore knowledge and seek information. In a …
This work designs an active world model learning system with progress-based curiosity.
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agen…
Rewards are sparse in the real world and most of today's reinforcement learning algorithms struggle with such sparsity. One solution to this problem is to allow the agent to create rewards for itself - thus making rewards dense and more suitable for learning. In particular, inspired by curious behaviour in animals, obs…
CCLF improves sample efficiency in RL by prioritizing informative samples.
Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot arm in simulation. Curiosity-driven exploration using the predict…
New method uses hindsight to make exploration robust in stochastic environments.
Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards. One promising strategy is inspired by human curiosity, requiring the agent to learn to predict the future. In this paper a curiosity-driven agent is extended to use these predictions di…
CUDC collects diverse data for offline RL by predicting future states.
Hyper addresses the hyperparameter tuning challenge in RL, improving exploration efficiency and robustness.
AutoOD automates outlier detection using curiosity-guided search and self-imitation learning.
Capsule Networks improve autonomous navigation in sparse environments.
Universal AI seeks high-optionality states through empowerment and curiosity.
Efficient method for choosing data points in machine learning models.
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace singl…
In this paper, we focus on a prediction-based novelty estimation strategy upon the deep reinforcement learning (DRL) framework, and present a flow-based intrinsic curiosity module (FICM) to exploit the prediction errors from optical flow estimation as exploration bonuses. We propose the concept of leveraging motion fea…
Curious Replay improves model-based reinforcement learning agents' adaptability.
In Reinforcement Learning (RL), an agent explores the environment and collects trajectories into the memory buffer for later learning. However, the collected trajectories can easily be imbalanced with respect to the achieved goal states. The problem of learning from imbalanced data is a well-known problem in supervised…
BYOL-Explore learns to explore visually-rich environments by predicting world dynamics.
BeBold improves exploration in sparse-reward tasks by regulating visitation counts.
Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically …
Expanding on a Heisenberg group case for a mathematical proposition.
Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to discover repertoires of policies producing a wide diversity of effects. Often th…
Interprets how intrinsic motivation shapes behavior in RL agents.
ACE improves GFlowNet exploration efficiency by balancing complementary search strategies.
The first part of this survey is a heuristic, non-technical discussion of what an HHS is, and the aim is to provide a good mental picture both to those actively doing research on HHSs and to those who only seek a basic understanding out of pure curiosity. It can be read independently of the second part, which is a deta…
New AI learns like neurons, generalizing from sparse rewards.
Unified framework for hybrid learning and optimization via active inference.
The ability of modeling the other agents, such as understanding their intentions and skills, is essential to an agent's interactions with other agents. Conventional agent modeling relies on passive observation from demonstrations. In this work, we propose an interactive agent modeling scheme enabled by encouraging an a…
This paper investigates the influence of different acoustic features, audio-events based features and automatic speech translation based lexical features in complex emotion recognition such as curiosity. Pretrained networks, namely, AudioSet Net, VoxCeleb Net and Deep Speech Net trained extensively for different speech…
We discuss the objectives of automation equipped with non-trivial decision making, or creating artificial intelligence, in the financial markets and provide a possible alternative. Intelligence might be an unintended consequence of curiosity left to roam free, best exemplified by a frolicking infant. For this unintenti…
New method uses mosaics to study wild knots.
New corks found that are not strong and exotic.
This paper presents the Homeo-Heterostatic Value Gradients (HHVG) algorithm as a formal account on the constructive interplay between boredom and curiosity which gives rise to effective exploration and superior forward model learning. We envisaged actions as instrumental in agent's own epistemic disclosure. This motiva…
Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like -greedy. This contributes to the problem of high sample complexity, as the algorithm wastes effort by repeatedly visiting parts of the state space that ha…
We investigate the use of attentional neural network layers in order to learn a `behavior characterization' which can be used to drive novelty search and curiosity-based policies. The space is structured towards answering a particular distribution of questions, which are used in a supervised way to train the attentiona…
Compactness theorem for timed-metric spaces established.
As spacecraft send back increasing amounts of telemetry data, improved anomaly detection systems are needed to lessen the monitoring burden placed on operations engineers and reduce operational risk. Current spacecraft monitoring systems only target a subset of anomaly types and often require costly expert knowledge to…