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.
Study task-guided exploration in linear dynamical systems, improving sample complexity.
In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encounters in the past while navigating a new task. Given an optimal policy in a related task-environment, we show that its bisimulation distance…
This paper investigates the effectiveness of adversarial training in enhancing the robustness of Deep Q-Network (DQN) policies to state-space perturbations. We first present a formal analysis of adversarial training in DQN agents and its performance with respect to the proportion of adversarial perturbations to nominal…
Reinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto a rewarding state. Recent works utilize intrinsic motivation to guide the exploration via generative models, predictive forward models, or …
Meta-SAGE improves deep RL scalability for CO tasks by adapting pre-trained models to larger-scale problems.
In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation, specifically the use of encoder-decoder networks, to learn associations between natural language behavior descriptions and state-action informatio…
We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to value function learning. We present several reinforcement learning algorithms that…
AGAC uses an adversary to enhance exploration in complex tasks.
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
The outcome of the explorative data analysis (EDA) phase is vital for successful data analysis. EDA is more effective when the user interacts with the system used to carry out the exploration. In the recently proposed paradigm of iterative data mining the user controls the exploration by inputting knowledge in the form…
Recursive KalmanNet generalizes well in noisy, out-of-distribution scenarios.
Guided Evolution improves NAS efficiency and accuracy.
Synthesizing programs using example input/outputs is a classic problem in artificial intelligence. We present a method for solving Programming By Example (PBE) problems by using a neural model to guide the search of a constraint logic programming system called miniKanren. Crucially, the neural model uses miniKanren's i…
Proximal policy optimization (PPO) is one of the most popular deep reinforcement learning (RL) methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, as a model-free RL method, the success of PPO relies heavily on the effectiveness of its exploratory policy search. In this pa…
Probabilistic programming languages (PPLs) are a powerful modeling tool, able to represent any computable probability distribution. Unfortunately, probabilistic program inference is often intractable, and existing PPLs mostly rely on expensive, approximate sampling-based methods. To alleviate this problem, one could tr…
Loss-guided training accelerates node embedding methods on graphs.
Study of motion constraints and path-following on 3D space.
When multiple agents learn in a decentralized manner, the environment appears non-stationary from the perspective of an individual agent due to the exploration and learning of the other agents. Recently proposed deep multi-agent reinforcement learning methods have tried to mitigate this non-stationarity by attempting t…
GE finds failures in autonomous systems without domain heuristics.
Guided Flows enhance sample quality in conditional image generation and text-to-speech.
Unified approach to guided generation techniques.
The Euclidean traveller explores various geometric spaces, seeing different places in each.
To realize efficient computational fluid dynamics (CFD) prediction of two-phase flow, a multi-scale framework was proposed in this paper by applying a physics-guided data-driven approach. Instrumental to this framework, Feature Similarity Measurement (FSM) technique was developed for error estimation in two-phase flow …
A new framework uses text descriptions to improve protein design.
Forest-guided smoothing uses random forest outputs for interpretable local smoothers.
The exploration mechanism used by a Deep Reinforcement Learning (RL) agent plays a key role in determining its sample efficiency. Thus, improving over random exploration is crucial to solve long-horizon tasks with sparse rewards. We propose to leverage an ensemble of partial solutions as teachers that guide the agent's…
Reinforcement Learning in domains with sparse rewards is a difficult problem, and a large part of the training process is often spent searching the state space in a more or less random fashion for any learning signals. For control problems, we often have some controller readily available which might be suboptimal but n…
ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.
BUSTLE synthesizes programs by learning from intermediate values.
Guided Learning improves end-to-end modeling for multi-stage decision-making.
Accelerates pulsar light curve inference with learned representations and optimization.
BeBold improves exploration in sparse-reward tasks by regulating visitation counts.
A single policy suffices for near-optimal parallel exploration in RL.
A new multi-objective RL framework improves intrinsic exploration performance.
New method predicts and optimizes test-time scaling for LLMs.
PAC-MCTS addresses biased search in LLM-guided planning by dynamically pruning.
An explorative data analysis system should be aware of what the user already knows and what the user wants to know of the data: otherwise the system cannot provide the user with the most informative and useful views of the data. We propose a principled way to do exploratory data analysis, where the user's background kn…
Max entropy exploration guides reinforcement learning agents to pursue achievable goals.
Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…
Curiosity enhanced by audio-visual associations improves learning efficiency.
DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.
This paper considers the problem of efficient exploration of unseen environments, a key challenge in AI. We propose a `learning to explore' framework where we learn a policy from a distribution of environments. At test time, presented with an unseen environment from the same distribution, the policy aims to generalize …
Study minimax optimal RL in factored MDPs with bonus exploration.
A method for self-supervised representation learning in partially observable environments.
This guide simplifies explainable deep learning for beginners.
Adaptive exploration scheme for evaluating multiple policies with different rewards.
NPENAS improves neural architecture search efficiency and accuracy.
Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions to guide policy behavior, lacking a mathematically-grounded objective with clear properties. In contrast, we recast exploration as a proble…