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 proposes a method to learn and exceed expert demonstrations in unknown reward environments.
Learning from demonstration (LfD) is the process of building behavioral models of a task from demonstrations provided by an expert. These models can be used e.g. for system control by generalizing the expert demonstrations to previously unencountered situations. Most LfD methods, however, make strong assumptions about …
Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is required. Some people use supervised learning to speed up the process of feature learning, others pretrain the policies by imitating expert dem…
Bayesian Experience Reuse improves learning from multiple experts.
Recent research has shown that although Reinforcement Learning (RL) can benefit from expert demonstration, it usually takes considerable efforts to obtain enough demonstration. The efforts prevent training decent RL agents with expert demonstration in practice. In this work, we propose Active Reinforcement Learning wit…
New model learns better policies from expert demonstrations with higher efficiency.
LEARN-SAM improves RL from sub-optimal demonstrations by localizing expert policies and selectively using demonstrations.
This work improves transferability of rewards inferred from expert demonstrations.
Multi-expert L2D underfits more severely, requiring new methods.
Novel framework learns policies from noisy expert demonstrations.
Reinforcement learning mimics expert behavior.
This paper reports applications of Difference of Convex functions (DC) programming to Learning from Demonstrations (LfD) and Reinforcement Learning (RL) with expert data. This is made possible because the norm of the Optimal Bellman Residual (OBR), which is at the heart of many RL and LfD algorithms, is DC. Improvement…
In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be perfect and sufficient, which yet is unrealistic to meet in practice. To work o…
Expert augmentation improves hybrid model generalization.
Improves online learning with expert demonstrations, quality matters.
Sigmoid gating is more sample efficient than softmax in mixture of experts.
KL-regularized RL from expert demos can lead to slow, unstable learning.
Improved time series forecasting with expert loss integration.
Sleep staging is a crucial task for diagnosing sleep disorders. It is tedious and complex as it can take a trained expert several hours to annotate just one patient's polysomnogram (PSG) from a single night. Although deep learning models have demonstrated state-of-the-art performance in automating sleep staging, interp…
NAMEx merges experts using Nash bargaining for improved performance.
The study tightens risk bounds for mixtures of experts using local differential privacy.
LMoE uses LLMs to improve stock trading by selecting experts based on textual and price data.
Improved HMoE models using Laplace gating function enhance expert specialization and performance.
Proposes -balancing for more balanced expert utilization in MoE models.
NDI learns from expert demonstrations by estimating occupancy measures.
This paper considers the problem of inverse reinforcement learning in zero-sum stochastic games when expert demonstrations are known to be not optimal. Compared to previous works that decouple agents in the game by assuming optimality in expert strategies, we introduce a new objective function that directly pits expert…
In order to improve forecasts, a decisionmaker often combines probabilities given by various sources, such as human experts and machine learning classifiers. When few training data are available, aggregation can be improved by incorporating prior knowledge about the event being forecasted and about salient properties o…
Online L2D algorithm for multiclass classification with varying experts.
ExpCLR uses expert features to improve time-series representation learning.
A new approach for learning from expert demonstrations using multiple perspectives.
We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed by reinforcement learning is indirect and may be computationally expensive. Rece…
In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate expert (or mentor), we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Com…
Existing imitation learning approaches often require that the complete demonstration data, including sequences of actions and states, are available. In this paper, we consider a more realistic and difficult scenario where a reinforcement learning agent only has access to the state sequences of an expert, while the expe…
Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising altern…
Budgeted deferral framework reduces expert query costs in machine learning.
System uses conformal prediction to help experts make accurate decisions without understanding when to trust it.
Recent work on imitation learning has generated policies that reproduce expert behavior from multi-modal data. However, past approaches have focused only on recreating a small number of distinct, expert maneuvers, or have relied on supervised learning techniques that produce unstable policies. This work extends InfoGAI…
One of the key advantages of Inductive Logic Programming systems is the ability of the domain experts to provide background knowledge as modes that allow for efficient search through the space of hypotheses. However, there is an inherent assumption that this expert should also be an ILP expert to provide effective mode…
Imitation Learning describes the problem of recovering an expert policy from demonstrations. While inverse reinforcement learning approaches are known to be very sample-efficient in terms of expert demonstrations, they usually require problem-dependent reward functions or a (task-)specific reward-function regularizatio…
Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functions, prior work on the topic has proposed several methods for reward estimation by using expert state trajectories and action pairs. However…
GWIL uses Gromov-Wasserstein distance to align expert and imitation agent states.
Demonstration-regularized RL reduces sample complexity for policy identification.
We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators of varying performance. We assume the demonstrators are classified into one of k ranks, and use ideas from ordinal regression to find a rewar…
A method merges two pretrained diffusion experts to improve image quality and likelihood.
Proposes GPHMEs using Gaussian processes for hierarchical expert models.
In this paper, we propose a hierarchical feature-aware tracking framework for efficient visual tracking. Recent years, ensembled trackers which combine multiple component trackers have achieved impressive performance. In ensembled trackers, the decision of results is usually a post-event process, i.e., tracking result …
We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a theoretical framework for the agent to optimize in the space of rewards consist…
Improved MoE performance through perturbing cosine router.