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.
Paper shows intrinsic motivation boosts exploration efficiency in HRL.
Framework learns useful subgoals from demonstrations and instructions.
Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects. However, due to the compounding uncertainty in long horizon video prediction and poor s…
Hierarchical Reinforcement Learning (HRL) exploits temporally extended actions, or options, to make decisions from a higher-dimensional perspective to alleviate the sparse reward problem, one of the most challenging problems in reinforcement learning. The majority of existing HRL algorithms require either significant m…
ISA learns subgoals for reinforcement learning agents.
The paper introduces an adjacency constraint to improve goal-conditioned HRL.
Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However, when the task distribution becomes wider, it would be quite inefficient to directly…
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, s…
A central challenge in reinforcement learning is discovering effective policies for tasks where rewards are sparsely distributed. We postulate that in the absence of useful reward signals, an effective exploration strategy should seek out {\it decision states}. These states lie at critical junctions in the state space …
Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories could help to learn faster. However, Imitation Learning (IL) via supervised pre-training with these trajectories may not perform as well and gen…
Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of the agent's policy can affect its exploration capabilities. First, we design EscapeRoom environments, where the agent must figure out how to n…
Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention. Instead of learning a global behavioral model, recent IRL methods divide the demonstration data i…
Most common navigation tasks in human environments require auxiliary arm interactions, e.g. opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks, which we call Interactive Navigation, requires the use of mobile manipulators: mobile bases with manipulation capabilities. Interactive N…
Deep learning optimizes VWAP strategy for lower transaction costs.
This paper presents a way of solving Markov Decision Processes that combines state abstraction and temporal abstraction. Specifically, we combine state aggregation with the options framework and demonstrate that they work well together and indeed it is only after one combines the two that the full benefit of each is re…
Prediction is arguably one of the most basic functions of an intelligent system. In general, the problem of predicting events in the future or between two waypoints is exceedingly difficult. However, most phenomena naturally pass through relatively predictable bottlenecks---while we cannot predict the precise trajector…
Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor ma…
We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments. The task emulates a real-world scenario in that (a) the requester may not know how to navigate to …
Differentiable causal discovery methods perform robustly under model violations.
New framework uses background knowledge to speed up causal discovery.
New method prevents invalid inference after causal discovery.
In many real-world scenarios, an autonomous agent often encounters various tasks within a single complex environment. We propose to build a graph abstraction over the environment structure to accelerate the learning of these tasks. Here, nodes are important points of interest (pivotal states) and edges represent feasib…
LDP speeds up causal discovery by partitioning, improving VAS recall and runtime.
Proposes LLM-DCD for improved causal discovery from data.
Many decision-making problems naturally exhibit pronounced structures inherited from the characteristics of the underlying environment. In a Markov decision process model, for example, two distinct states can have inherently related semantics or encode resembling physical state configurations. This often implies locall…
Probabilistic grammars improve equation discovery from data.
Causal discovery improves fMRI analysis, but faces challenges.
New methods for Markov Blanket discovery using MML outperform existing approaches.
L2D-CD learns to defer expert recommendations in causal discovery.
Building systems that autonomously create temporal abstractions from data is a key challenge in scaling learning and planning in reinforcement learning. One popular approach for addressing this challenge is the options framework (Sutton et al., 1999). However, only recently in (Bacon et al., 2017) was a policy gradient…
Review of automation's role in chemical discovery, emphasizing future challenges.
New method controls false discoveries in financial asset pricing.
Interpretable ML helps discover insights from big data.
We introduce interactive structure discovery, a generic framework that encompasses many interactive learning settings, including active learning, top-k item identification, interactive drug discovery, and others. We adapt a recently developed active learning algorithm of Tosh and Dasgupta (2017) for interactive structu…
Review of automation's role in chemical discoveries.
KEEL improves causal discovery with fuzzy knowledge and complex data.
Cluster-DAGs improve causal discovery with prior knowledge.
The paper examines how timing of observations affects causal discovery methods.
New algorithm improves materials discovery using max K-Armed Bandit.
This work integrates domain knowledge into A*-based causal discovery methods.
New methods control false discoveries near the boundary in conformal novelty detection.
Paper presents a new dataset for testing causal discovery methods in industrial systems.
Python library for causal discovery from observational data.
The paper establishes bounds for score-matching in causal discovery and generative modeling.
The aim of process discovery, originating from the area of process mining, is to discover a process model based on business process execution data. A majority of process discovery techniques relies on an event log as an input. An event log is a static source of historical data capturing the execution of a business proc…
Visualizes deep generative models for drug design.
Paper discovers structural dynamics equations from only acceleration data.
Process discovery has seen a rise in popularity in the last decade for both researchers and businesses. Recent developments mainly focused on the power and the functionalities of the discovery algorithm. While continuous improvement of these functional aspects is very important, non-functional aspects such as visualiza…