Paper improves RL from imperfect demonstrations with soft expert guidance.
problem Improper and insufficient expert demonstrations in RLfD.
method Formalizes imperfect expert setting, tackles optimality and convergence issues with soft constraints, and uses local linear search on dual form.
result Method achieves consistent improvement over other RLfD methods.
GH-PID uses guided harmonic paths for efficient SOT with interpretable diagnostics.
problem Efficiently solving Stochastic Optimal Transport with hard terminal distributions and soft costs.
method Guided Harmonic Path-Integral Diffusion (GH-PID) framework with low-dimensional guidance.
result GH-PID generates geometry-aware, cost-reducing trajectories that match terminal distributions.
LEAQI learns to query an expert less often for noisy guidance.
problem Active imitation learning with noisy guidance to reduce expert query complexity.
method Developed LEAQI, a difference classifier that predicts expert disagreement with noisy heuristic.
result Significantly fewer queries to the expert with comparable or better accuracy.
DSAC improves robustness of imitation learning.
problem Learning from few expert data and distribution shift.
method DSAC uses adversarial reward function.
result DSAC performs well on PyBullet environments.
New method optimizes diffusion models without fine-tuning, integrating soft value functions.
problem Optimizing natural design spaces of images, molecules, DNA, RNA, and protein sequences.
method Iterative sampling method integrating soft value functions into diffusion model inference.
result Directly utilizes non-differentiable features/reward feedback, applies to discrete diffusion models.
Adversarial MoE learns category-specific models for product search.
problem Variations in product features and importance across categories.
method Mixture of Experts with adversarial regularization and soft gating constraints.
result Improved clustering of gate output vectors and shared experts among similar categories.
Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms. Pretraining reinforcement learning remains a significant challenge i…
Regression problems assume every instance is annotated (labeled) with a real value, a form of annotation we call \emph{strong guidance}. In order for these annotations to be accurate, they must be the result of a precise experiment or measurement. However, in some cases additional \emph{weak guidance} might be given by…
Dropout is a very effective method in preventing overfitting and has become the go-to regularizer for multi-layer neural networks in recent years. Hierarchical mixture of experts is a hierarchically gated model that defines a soft decision tree where leaves correspond to experts and decision nodes correspond to gating …
The abstract explores connections between reinforcement learning, scaling, and diffusion.
problem Aligning reinforcement learning with human feedback and scaling techniques.
method Clarifying connections between reinforcement learning, scaling, and diffusion.
result Introducing a resampling approach for alignment and reward-directed diffusion models.
Deep reinforcement learning has achieved great successes in recent years, however, one main challenge is the sample inefficiency. In this paper, we focus on how to use action guidance by means of a non-expert demonstrator to improve sample efficiency in a domain with sparse, delayed, and possibly deceptive rewards: the…
Enhances RL performance with a population-guided parallel learning scheme.
problem Improving off-policy reinforcement learning performance.
method Population-guided parallel learning scheme with shared experience replay buffer and soft policy update.
result Monotone improvement of the expected cumulative return proved theoretically and demonstrated in practice.
End-to-end CAD system for thyroid nodule classification using multimodal data and expert guidance.
problem Improving accuracy in thyroid nodule classification for clinicians.
method Knowledge-driven DenseNet framework using multimodal ultrasound data and expert cues.
result The proposed system achieves relevant performances in thyroid nodule classification.
STAR improves equivariant and invariant representation learning by routing projection heads.
problem Redundant feature learning in equivariant and invariant representation learning.
method Soft Task-Aware Routing (STAR) for projection heads specialization.
result Lower canonical correlations between invariant and equivariant embeddings.
System guides freehand obstetric ultrasound probe movements.
problem Reducing operator expertise for standard plane acquisition.
method Artificial neural network trained on real scans.
result 88.8% accuracy for goal prediction, 90.9% for action prediction.
GSI improves efficiency of large language model inference.
problem Efficiently guiding test-time alignment in large language models.
method Combines soft best-of-n scaling with a reward model and speculative samples. result Achieves higher accuracy and reduced latency compared to standard methods.
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…
MODULE solves LfO problem with high sample efficiency and stability.
problem Sample inefficiency and instability in LfO.
method Modified DSAC with MODULE algorithm.
result Superior performance in MuJoCo environments.
We consider prediction with expert advice under the log-loss with the goal of deriving efficient and robust algorithms. We argue that existing algorithms such as exponentiated gradient, online gradient descent and online Newton step do not adequately satisfy both requirements. Our main contribution is an analysis of th…
We study how to effectively leverage expert feedback to learn sequential decision-making policies. We focus on problems with sparse rewards and long time horizons, which typically pose significant challenges in reinforcement learning. We propose an algorithmic framework, called hierarchical guidance, that leverages the…
Survey of methods for learning from observation without requiring expert actions.
problem Lack of access to expert actions in imitation learning.
method Survey and classification of state-only imitation learning (SOIL) methods.
result Identification of open problems and future research directions.
In regression tasks the distribution of the data is often too complex to be fitted by a single model. In contrast, partition-based models are developed where data is divided and fitted by local models. These models partition the input space and do not leverage the input-output dependency of multimodal-distributed data,…
Logistic regression can handle noisy labels effectively when labels are imperfectly assigned by multiple experts.
problem Label noise in supervised classification due to manual labelling by multiple experts.
method Using approximate posterior probabilities of class membership from multiple experts to train logistic regression models.
result Logistic regression can be robust to label noise when classification difficulty is the only source of errors.
New approach transfers rewards learned in one environment to reinforcement learning in a new environment.
problem Transfer of rewards learned using inverse reinforcement learning from one environment to a new, different environment.
method Formulate the problem as a joint system of Bellman equations, develop minimax estimators for the target soft-q-function, solve the source and target system of equations jointly. result The coupled approach removes the first-order influence of source Bellman residual error compared to the sequential approach.
L2D-CD learns to defer expert recommendations in causal discovery.
problem Combining expert knowledge with data-driven results in causal discovery when expert recommendations may contradict data.
method Adapting learning-to-defer algorithms for pairwise causal discovery, L2D-CD learns a deferral function to select between expert recommendations and data-driven methods.
result L2D-CD outperforms both causal discovery methods and the expert used in isolation, identifying domains where the expert's performance is strong or weak.
Tutorial on optimizing diffusion model samples for specific metrics.
problem Optimizing diffusion model samples for specific downstream metrics.
method Review and exploration of inference-time guidance and alignment methods.
result Unified perspective on inference-time algorithms and novel methods.
The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant expert demonstrations or the explicitly-coded cost function on targe…
A new method removes policy optimization in adversarial imitation learning.
problem Adversarial imitation learning's delicate alternated optimization.
method Explicitly condition discriminator on two policies, solving generator's optimization problem directly.
result Simpler approach competitive to prevalent methods.
A RL-based method adds conditional controls to pre-trained diffusion models.
problem Precise control over generated samples in diffusion models.
method Formulates the task as an RL problem, using a classifier and KL divergence as reward functions.
result Produces soft-optimal policies that maximize reward functions, enabling conditional sampling.
Learning to drive faithfully in highly stochastic urban settings remains an open problem. To that end, we propose a Multi-task Learning from Demonstration (MT-LfD) framework which uses supervised auxiliary task prediction to guide the main task of predicting the driving commands. Our framework involves an end-to-end tr…
EQD model improves domain-specific QA by 0.6% to 10.5%.
problem Challenges in domain-specific quantitative reasoning for LLMs.
method Two-step fine-tuning framework guided by a reward function.
result EQD outperforms state-of-the-art models and prompting strategies.
Improved SAC with AWMP for better control tasks.
problem Discontinuous and non-smooth optimal policies in reinforcement learning.
method Advantage Weighted Mixture Policy (AWMP) for SAC, learning state-specific weights.
result SAC with AWMP outperforms SAC in four control tasks.
SelectMix improves deep learning robustness against noisy labels.
problem Deep neural networks memorize noisy labels, degrading performance.
method Confidence-guided targeted sample mixing with soft labels.
result SelectMix consistently outperforms baseline methods on noisy label datasets.
Develops statistical framework for resolving reward function ambiguity in inverse reinforcement learning.
problem Non-uniqueness of reward functions in inverse reinforcement learning.
method Entropy regularization combined with least-squares reconstruction of the reward from the soft Bellman residual.
result Least-squares reward function is unique and consistent with the expert policy.
Unified scoring model improves efficiency and performance across multiple tasks.
problem Efficient and resource-efficient automated scoring for diverse tasks.
method Knowledge-distilled multi-task Mixture-of-Experts (MoE) approach.
result Comparable performance to task-specific models with significantly less storage and training resources.
CNNs identify stock market trend endpoints based on expert opinion.
problem Finding optimal entry and exit points for stock market trends.
method Three CNN submodels sequentially identify changepoints, locate them, and classify trends as upward, downward, or flat.
result CNNs can identify long-term trends based on expert opinion, offering a new approach to stock market analysis.
FinSphere improves stock analysis quality with AI and expert-curated data.
problem Lack of objective evaluation metrics and depth in stock analysis by FinLLMs.
method Developed AnalyScore, curated Stocksis dataset, and FinSphere AI agent.
result FinSphere outperforms general and domain-specific LLMs in generating high-quality stock analysis reports.
This paper studies Learning from Observations (LfO) for imitation learning with access to state-only demonstrations. In contrast to Learning from Demonstration (LfD) that involves both action and state supervision, LfO is more practical in leveraging previously inapplicable resources (e.g. videos), yet more challenging…
Proposes a framework to improve domain adaptation without labeled data.
problem Improving adaptability and preserving intrinsic data structure in unsupervised domain adaptation.
method Discriminative Manifold Propagation framework using soft labels and manifold metric alignment.
result The method achieves better transferability and discriminability compared to existing approaches.
Neural A* uses machine learning to improve path planning efficiency.
problem Challenges in applying machine learning to search-based path planning.
method Reformulated A* search as a differentiable network coupled with a convolutional encoder.
result Neural A* outperforms state-of-the-art planners in optimality and efficiency.
The Hierarchical Mixture of Experts (HME) is a well-known tree-based model for regression and classification, based on soft probabilistic splits. In its original formulation it was trained by maximum likelihood, and is therefore prone to over-fitting. Furthermore the maximum likelihood framework offers no natural metri…
A new method for optimizing models with categorical variables using diffusion.
problem Optimizing models with categorical variables, especially in discrete distributions.
method Introducing ReDGE, a diffusion-based soft reparameterization method for categorical distributions.
result ReDGE consistently matches or outperforms existing gradient-based methods in experiments.
This work formalizes guidance in diffusion models and introduces a stochastic control framework.
problem Lack of a solid theoretical foundation for guidance scheduling in diffusion models.
method Introduces a stochastic optimal control framework to cast guidance scheduling as an adaptive optimization problem.
result Establishes a principled foundation for more effective guidance in diffusion models.
Framework for training-free guidance in discrete diffusion models for molecular generation.
problem No equivalent training-free guidance methods for discrete diffusion models.
method Framework using guidance functions for discrete data.
result Demonstrated utility on molecular graph generation tasks.
Exact guidance for discrete data improves posterior sampling efficiency.
problem Inefficient guidance for discrete data in posterior sampling.
method Derive exact transition rate for desired distribution given learned discrete flow matching model.
result Significantly improved efficiency with single forward pass per sampling step.
Diffusion models improve sample quality with guidance, proving it works for general data distributions.
problem Theoretical understanding of guidance effect in diffusion models for general data distributions.
method Analyzing diffusion guidance under general data distributions, proving improvement in sample quality.
result Guidance improves the average reciprocal of the classifier probability, aligning with its motivation.
URGE improves diffusion model quality without gradients or Hessian.
problem Improving sample quality in diffusion models without gradient evaluations.
method Path-wise importance reweighting via Girsanov change of measure.
result URGE achieves better generation quality than existing methods.
Research shows guidance in diffusion models does not sample from intended distribution, affecting boundary sampling.
problem Clarifying the misconception that guidance modifies the data distribution in diffusion models.
method Rigorous proof and fine-grained analysis of guidance dynamics in two cases: mixtures of compactly supported distributions and mixtures of Gaussians.
result Guidance leads to sampling more heavily from the boundary of the support of the conditional distribution as the parameter increases.