Deep reinforcement learning has led to several recent breakthroughs, though the learned policies are often based on black-box neural networks. This makes them difficult to interpret and to impose desired specification constraints during learning. We present an iterative framework, MORL, for improving the learned polici…
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “policy synthesis”
SafePILCO is a Python tool for safe reinforcement learning.
problem Safe and efficient policy synthesis in reinforcement learning.
method Extends PILCO algorithm with safety features, implemented in Python.
result Safe and data-efficient policy synthesis achieved.
The problem of retrosynthetic planning can be framed as one player game, in which the chemist (or a computer program) works backwards from a molecular target to simpler starting materials though a series of choices regarding which reactions to perform. This game is challenging as the combinatorial space of possible cho…
CrossBeam learns to search more efficiently in program synthesis.
problem Efficiently searching through vast program spaces.
method Trains a neural model to guide program synthesis, combining previously explored programs.
result CrossBeam explores much smaller portions of the program space compared to state-of-the-art methods.
DeepSynth synthesizes automata to guide deep RL agents through sparse, non-Markovian rewards.
problem Training deep RL agents with sparse, non-Markovian rewards and unknown high-level objectives.
method Employing a novel algorithm for synthesizing compact automata to uncover sequential structure from trace data.
result Reduces the number of iterations required for policy synthesis by two orders of magnitude and improves scalability.
Survey of theoretical foundations for policy optimization in control.
problem Understanding the theoretical properties of gradient-based methods in control and reinforcement learning.
method Interdisciplinary review of optimization landscape, convergence, and sample complexity for various control problems.
result Recent theoretical results on stability and robustness in learning-based control.
Neural Lyapunov Redesigneess.SY
Combines Lyapunov functions with controller synthesis for safe control policies.
problem Ensuring safety in controller design for nonlinear systems.
method Iterative algorithm combining Lyapunov function estimation and controller synthesis.
result Effective control policies with large safe regions are derived.
We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate. MAPO is applicable to deterministic environments with discrete actions, such as structured prediction and combinatorial optimization ta…
This paper solves steady-state planning for multichain MDPs.
problem Specifying constraints on the steady-state behavior of an agent.
method Linear programming solution for multichain MDPs.
result Optimal solutions yield stationary policies with rigorous guarantees.
A novel framework uses goal-conditioned reinforcement learning to generate diverse samples.
problem Generating high-quality, diverse samples from generative models.
method Two agents: GC-agent learns to reconstruct the training set, S-agent learns to imitate GC-agent without knowing the goals.
result Empirically, the method generates diverse and high-quality samples in image synthesis.
Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?cs.LG
Long horizon reinforcement learning is as hard as short horizon learning.
problem Understanding the difficulty of long horizon reinforcement learning problems.
method Introduced new concepts: ε-net for optimal policies and Online Trajectory Synthesis algorithm.
result Proved that sample complexity scales logarithmically with the planning horizon, refuting the conjecture.
Safe reinforcement learning with logical constraints for optimal policy synthesis.
problem Ensuring safety during reinforcement learning while maximizing goal satisfaction.
method Adaptive safe padding that synthesizes optimal control policies satisfying temporal logic formulas.
result The proposed method handles the trade-off between exploration and safety with theoretical guarantees.
RFC enhances humanoid control to imitate complex human motions.
problem Dynamics mismatch between humanoid models and real humans.
method Residual Force Control (RFC) augments control policies with external forces.
result RFC outperforms state-of-the-art methods in convergence speed and motion quality.
Paper proposes a method for optimizing local policies for trajectory-centric reinforcement learning.
problem Challenges in global policy optimization for non-linear systems and poor performance of open-loop trajectory optimization.
method Formulates trajectory optimization and local policy synthesis as a single optimization problem and solves it as a nonlinear programming instance.
result Demonstrates improved performance of the proposed technique under simplifying assumptions.
We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to formal verification than neural policies; however, designing rigorous learning approaches for such poli…
The paper optimizes policies constrained to Schur stabilizing controllers using a Newton-type algorithm.
problem Optimizing policies under linear constraints in control systems.
method Newton-type algorithm on a manifold of Schur stabilizing controllers with a Riemannian metric.
result Local convergence guarantees for the Newton-type algorithm without relying on exponential mapping or retractions.
We propose a method for efficient training of Q-functions for continuous-state Markov Decision Processes (MDPs) such that the traces of the resulting policies satisfy a given Linear Temporal Logic (LTL) property. LTL, a modal logic, can express a wide range of time-dependent logical properties (including "safety") that…
Learning policies on data synthesized by models can in principle quench the thirst of reinforcement learning algorithms for large amounts of real experience, which is often costly to acquire. However, simulating plausible experience de novo is a hard problem for many complex environments, often resulting in biases for …
Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of learning control policies for unknown linear dynamical systems so as to maximize…
Improved text-to-image and multimodal understanding through adaptive generation order optimization.
problem Determining optimal generation sequences in text-to-image synthesis and multimodal understanding.
method Introduced a learnable control module trained via Group Relative Policy Optimization (GRPO) to determine the generation order.
result Learning the control block substantially improves text-to-image alignment and multimodal understanding in DLMs.
Tree-based synthesis improves forecast accuracy in GDP and inflation.
problem Improving forecast accuracy in GDP and inflation.
method Developed a nonparametric synthesis function using regression trees.
result Tree-based synthesis leads to improved forecast accuracy.
Despite the tremendous advances that have been made in the last decade on developing useful machine-learning applications, their wider adoption has been hindered by the lack of strong assurance guarantees that can be made about their behavior. In this paper, we consider how formal verification techniques developed for …
Speech Synthesis using EEGeess.AS
Speech synthesis from EEG features using RNN.
problem Speech synthesis from EEG data.
method Recurrent Neural Network (RNN) regression model to predict acoustic features from EEG features.
result Feasibility of synthesizing speech directly from EEG features demonstrated.
SED integrates synthesis, execution, and debugging for neural program synthesis.
problem Challenges in synthesizing complex programs that match specifications.
method SED combines synthesis, execution, and debugging to improve neural program generation.
result SED reduces error rates and outperforms standard decoding methods.
Retro* uses neural networks to efficiently find high-quality synthetic routes in organic chemistry.
problem Finding efficient synthetic routes in organic chemistry is challenging due to the vast search space.
method Retro* is a neural-based A*-like algorithm that learns a neural search bias to guide efficient best-first search.
result Retro* outperforms existing methods in both success rate and solution quality while being more efficient.
The recent success of raw audio waveform synthesis models like WaveNet motivates a new approach for music synthesis, in which the entire process --- creating audio samples from a score and instrument information --- is modeled using generative neural networks. This paper describes a neural music synthesis model with fl…
System uses machine learning and automated reasoning to speed up PBE synthesis.
problem Slow synthesis in PBE due to domain-specific knowledge and large training datasets.
method Preprocess SyGuS PBE problems with a neural network to reduce search space, then use automated reasoning for faster solution.
result System outperforms all competing tools in the 2019 SyGuS Competition for the PBE Strings track by 47.65%.
The discovery of processes for the synthesis of new materials involves many decisions about process design, operation, and material properties. Experimentation is crucial but as complexity increases, exploration of variables can become impractical using traditional combinatorial approaches. We describe an iterative met…
A neural program synthesis method with iterative fix operations.
problem Creating correct programs from input-output examples.
method Combines encoder-decoder synthesis with a differentiable fixer.
result Improves synthesis accuracy by reducing discrepancies between outputs and desired outputs.
New approach generates better synthetic data for neural program synthesis.
problem Current approaches to neural program synthesis generalize poorly to real data.
method Adversarial approach to control synthetic data distributions.
result Proposed method outperforms current approaches.
We prove that spherical spectral analysis and synthesis hold in Damek-Ricci spaces and derive two-radius theorems.
Generative model creates realistic scenes from pixel-wise labels.
problem Creating photo-realistic scenes from pixel-wise labels.
method Semantic bottleneck GAN model combining conditional and unconditional generation networks.
result Model outperforms state-of-the-art models in unsupervised image synthesis.
The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesiscs.SD
Inverse Drum Machine separates drum mixes using transcription and synthesis.
problem Separating individual drum tracks from mixed recordings.
method Analysis-by-synthesis framework combining deep learning and automatic transcription.
result Separation quality comparable to supervised methods requiring isolated stems.
Adaptive correlated MC improves sequence generation stability.
problem High gradient variance in reinforcement learning for sequence generation.
method Adapts policy gradient estimator using correlated Monte Carlo rollouts.
result Reduces gradient variance and improves model performance.
Language models predict inorganic synthesis conditions and temperatures.
problem Limited data and heuristic approaches constrain inorganic synthesis planning.
method Language models without fine-tuning predict precursor conditions and temperatures.
result Language models achieve high accuracy in predicting synthesis conditions and temperatures.
Exemplar-based synthesis of geology using kernel discrepancies and generative neural networksstat.ML
We propose a framework for synthesis of geological images based on an exemplar image. We synthesize new realizations such that the discrepancy in the patch distribution between the realizations and the exemplar image is minimized. Such discrepancy is quantified using a kernel method for two-sample test called maximum m…
BOiLS optimizes circuit quality using Bayesian optimization.
problem Optimizing circuits with complex search spaces.
method Adapting Bayesian optimization to logic synthesis, using Gaussian process kernels and trust-region constrained acquisitions.
result Demonstrated superior performance in sample efficiency and QoR values.
AutoDiff combines auto-encoder and diffusion model for realistic tabular data synthesis.
problem Generating realistic synthetic tabular data with heterogeneous features.
method Employing auto-encoder architecture to handle tabular data's complexity.
result Synthetic tables from AutoDiff show good statistical fidelity and perform well in machine learning tasks.
Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology. In this paper we present a model-free RL algorithm to synthesize control policies that maximize the probability of satisfying h…
Diffusion models outperform GANs in image synthesis quality.
problem Improving image synthesis quality using generative models.
method Developed and optimized diffusion models, and introduced classifier guidance for conditional synthesis.
result Achieved superior image synthesis quality with diffusion models, matching or exceeding GANs in FID scores.
A fundamental problem in control is to learn a model of a system from observations that is useful for controller synthesis. To provide good performance guarantees, existing methods must assume that the real system is in the class of models considered during learning. We present an iterative method with strong guarantee…
Develops BPDS for better financial portfolio decisions.
problem Model uncertainty in financial time series forecasting.
method Bayesian dynamic modelling and predictive decision synthesis.
result Improved predictive and decision outcomes compared to traditional Bayesian analysis.
Program synthesis struggles with complex spatial relationships in image classification.
problem Challenges in solving Synthetic Visual Reasoning Test problems.
method Quantitative reanalysis of human and machine performance, improved program synthesis classifier, categorization of SVRT problems.
result Program synthesis is constrained by spatial relationships in images, not just shape specification.
Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Modelseess.AS
Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural networks (DNNs). However, a limitation is the lack of synchronized audio, video, an…
WaveCycleGAN has recently been proposed to bridge the gap between natural and synthesized speech waveforms in statistical parametric speech synthesis and provides fast inference with a moving average model rather than an autoregressive model and high-quality speech synthesis with the adversarial training. However, the …
Model for directed synthesis of audio textures using multi-scale RNNs.
problem Challenges in modeling complex audio textures with traditional methods.
method Combining multi-scale RNNs with a conditioning strategy for user-directed synthesis.
result Demonstrated improved performance on various audio texture datasets.
We present a program synthesis-oriented dataset consisting of human written problem statements and solutions for these problems. The problem statements were collected via crowdsourcing and the program solutions were extracted from human-written solutions in programming competitions, accompanied by input/output examples…
Proposes a synthesis algorithm using Conformal Prediction for improved Deep Learning performance.
problem Assessing the quality of synthesised data for high-stake domains.
method Conformal Prediction framework for generating data from high-confidence feature space regions.
result Training sets extended with confident synthesised data improved Deep Learning performance by up to 61 percentage points F1-score.