Introduces LoCA regret to evaluate model-based RL methods.
problem Lack of consistent metrics to evaluate model-based RL methods.
method Inspired by neuroscience, introduces LoCA regret to measure model-based behavior.
result LoCA regret can identify model-based behavior and assess how close methods are to optimal model-based behavior.
We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model is trained end-to-end via back-propagation. Despite being trained using the mode…
New method reduces variance in subpopulation model performance estimates.
problem High variance in subpopulation performance metrics for small groups.
method Using an evaluation model to form model-based metric (MBM) estimates.
result MBMs produce more accurate and lower variance estimates for small subpopulations.
The aim of this paper is to develop on the 1-jet space J^1(R,M^4) the jet Generalized Lagrange Geometry for the rheonomic Chernov metric. The associated gravitational and electromagnetic field models based on the rheonomic Finsler Chernov metric tensor are developed and discussed.
Study validates metrics for offline MBO using diffusion models.
problem Evaluate metrics for offline MBO without ground truth oracle.
method Propose and quantify validation metrics over datasets.
result Identify most effective validation metrics.
The paper develops the Finsler-like geometry on the 1-jet space for the jet conformal Minkowski (JCM) metric, which naturally extends the Minkowski metric in the Chernov-Pavlov framework. To this aim there are determined the nonlinear connection, distinguished (d-) Cartan linear connection, d-torsions and d-curvatures.…
We examine the impact of learning Lipschitz continuous models in the context of model-based reinforcement learning. We provide a novel bound on multi-step prediction error of Lipschitz models where we quantify the error using the Wasserstein metric. We go on to prove an error bound for the value-function estimate arisi…
The development of models for learning music similarity and feature extraction from audio media files is an increasingly important task for the entertainment industry. This work proposes a novel music classification model based on metric learning and feature extraction from MP3 audio files. The metric learning process …
Paper proposes a new framework to improve policy optimization by aligning real and simulated data distributions.
problem Inaccurate model estimation leads to performance degradation in model-based reinforcement learning.
method Introduces unsupervised model adaptation to minimize the IPM between real and simulated data distributions.
result Achieves state-of-the-art performance in sample efficiency on various continuous control tasks.
Learning a generative model is a key component of model-based reinforcement learning. Though learning a good model in the tabular setting is a simple task, learning a useful model in the approximate setting is challenging. In this context, an important question is the loss function used for model learning as varying th…
Proposes FMC for fair clustering with independent parameters.
problem Finding clusters with balanced sensitive attribute proportions.
method Model-based clustering using finite mixture model with mini-batch learning.
result FMC scales up easily and can handle non-metric data.
A new algorithm STE for model-based RL improves learning rates.
problem Sparse rewards and computational intractability of estimating information gain.
method Developed a novel algorithm based on Stein Information Directed Exploration (STE)E.
result Achieves sublinear Bayesian regret, outperforming prior approaches.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
problem Model-based policy learning in uncertain, time-varying dynamics.
method Planning regret metric and iterative algorithm for minimizing it.
result Empirical evidence shows the proposed algorithm outperforms existing methods.
Single autoregressive model outperforms ensemble methods in offline reinforcement learning.
problem Offline reinforcement learning with limited data and model errors.
method Infer system dynamics from data and optimize policies on model rollouts, using a single autoregressive model.
result Single autoregressive model achieves better performance than ensembles on the D4RL benchmark.
Combines model-based and model-free RL for better financial market performance.
problem Challenges of Reinforcement Learning in volatile financial markets.
method Adapts model-based RL with model-free RL, incorporating contextual signals and walk-forward analysis.
result Outperforms traditional financial models in various metrics.
Despite the growing importance of multilingual aspect of web search, no appropriate offline metrics to evaluate its quality are proposed so far. At the same time, personal language preferences can be regarded as intents of a query. This approach translates the multilingual search problem into a particular task of searc…
Simple model-based reinforcement learning outperforms model-free methods in complex tasks.
problem Lagging performance of model-based reinforcement learning agents in non-trivial environments.
method Combining soft value estimates with stochastic value gradients.
result Simple model-based agents achieve state-of-the-art results in a high-dimensional humanoid control task.
POMBU improves model-based RL's asymptotic performance by estimating and using uncertainty.
problem Model-based reinforcement learning struggles with model errors, leading to suboptimal performance.
method POMBU uses estimated uncertainty to optimize policies conservatively, improving asymptotic performance.
result POMBU outperforms existing methods in sample efficiency and asymptotic performance.
M3PO improves model-based meta-RL with theoretical guarantees.
problem Improving sample efficiency in multi-task RL with theoretical guarantees.
method Extending Janner et al. (2019) theorems, proposing M3PO with performance guarantees.
result M3PO outperforms existing methods in continuous-control benchmarks.
This paper improves Bayesian inference for predictive models with limited data.
problem Effective uncertainty quantification for training predictive models with limited data.
method Entropy-regularized gradient estimators to approximate the Bayesian posterior.
result The method generates diverse samples from the posterior distribution efficiently.
Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-…
Model-based neural networks generalize better than ReLU networks for sparse recovery.
problem Understanding and quantifying the superior generalization of model-based neural networks.
method Using complexity measures like global and local Rademacher complexities, the paper provides theoretical bounds on generalization and estimation errors.
result Model-based neural networks exhibit higher generalization capabilities for sparse recovery problems compared to ReLU networks.
Study batch reinforcement learning methods for personalized medical treatments.
problem Batch reinforcement learning for personalized medical treatments.
method Direct policy learning and model-based learning approaches.
result Model-based learning is impossible with finite model classes but feasible with relaxed conditions.
Model-based machine learning improves communication systems.
problem Improving symbol detection in communication receivers.
method Review and comparison of model-based and deep learning approaches, focusing on deep unfolding and DNN-aided hybrid algorithms.
result Different strategies of conventional deep architectures and hybrid algorithms show advantages and drawbacks.
A new method reduces compounding errors in model-based reinforcement learning.
problem Compounding errors in long horizon predictions from model-based reinforcement learning.
method Maximum Entropy Model Rollouts (MEMR) with non-uniform sampling and prioritized experience replay.
result Significantly reduces computation requirements compared to other model-based methods.
A framework schedules hyperparameters for model-based reinforcement learning, improving performance.
problem Inadequate scheduling of hyperparameters in model-based reinforcement learning.
method Theoretical analysis and AutoMBPO framework to automatically schedule real data ratio and other hyperparameters.
result Training with hyperparameters scheduled by AutoMBPO significantly improves performance.
Paper develops a model-based RL framework for portfolio optimization in financial markets.
problem Complex, non-Gaussian environment dynamics in financial markets.
method Heavy-tailed preserving normalizing flows for environment simulation; model-based reinforcement learning framework.
result Proposed method outperforms in various financial markets, especially during the pandemic.
SAMBA improves safe reinforcement learning with active exploration metrics.
problem Safe reinforcement learning in dynamic systems.
method Combines probabilistic modelling, information theory, and statistics. Uses novel metrics for out-of-sample Gaussian process evaluation.
result Orders of magnitude reduction in samples and violations compared to state-of-the-art methods.
Paired autoencoders solve inverse problems using latent space projections.
problem Solving inverse problems in scientific computing.
method Paired autoencoder framework that projects data and quantity of interest into a latent space.
result Paired autoencoders generate multiple reconstruction metrics and enable latent-space refinement for accurate data fitting.
Graph neural network learns graph distances effectively.
problem Maintaining graph distance metric properties.
method GRAPH-BERT based semi-supervised distance metric learning.
result GB-DISTANCE outperforms existing methods.
Clarifies model-based RL's theoretical issues and counterexamples for popular losses.
problem Model-based reinforcement learning's empirical performance vs. theoretical properties and popular loss functions.
method Analyzes empirical and theoretical aspects of model-based RL and constructs counterexamples for losses.
result MuZero loss fails in stochastic and deterministic environments, leading to exponential sample complexity.
The paper uses model-based trees to create interpretable surrogate models for complex machine learning models.
problem Interpreting complex machine learning models.
method Using model-based trees to partition feature space and create interpretable models.
result Model-based trees generate optimal surrogate models that balance interpretability and performance.
Asynchronous framework speeds up model-based RL to real-time.
problem Real-time learning on real robots with model-based RL.
method Asynchronous framework for model-based reinforcement learning.
result Reduced run time to data collection time, improved sample complexity.
Unified framework for model-based RL with sample complexity guarantees.
problem Designing efficient posterior sampling methods for model-based RL.
method Optimistic posterior sampling, Hellinger distance reduction, data likelihood measurement.
result Unified algorithms with state-of-the-art sample complexity guarantees.
Unified reinforcement learning methods using hybrid inference.
problem Combining model-based and model-free reinforcement learning approaches.
method Control as Hybrid Inference (CHI) framework.
result CHI algorithm balances model-based and model-free learning.
Model-free Reinforcement Learning (RL) algorithms such as Q-learning [Watkins, Dayan 92] have been widely used in practice and can achieve human level performance in applications such as video games [Mnih et al. 15]. Recently, equipped with the idea of optimism in the face of uncertainty, Q-learning algorithms [Jin, Al…
Survey of integrating planning and learning in model-based reinforcement learning.
problem Sequential decision making in AI, formalized as MDP optimization.
method Systematic coverage of dynamics model learning and planning-learning integration.
result Broad conceptual overview of model-based reinforcement learning.
Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inaccurate and impose a bottleneck on performance. This paper explores which uncertainties are needed for…
MoMA improves model-based RL by using unrestricted policy classes.
problem Limited sample efficiency and generalizability in model-based offline RL.
method Model-based mirror ascent algorithm with general function approximations.
result Theoretical guarantees and practical implementation of MoMA.
Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data. In this paper, we study the role of model usage in policy optimization both theoretically and empirically. We first formulate and analyze a model-b…
We give an explicit algorithm and source code for constructing risk models based on machine learning techniques. The resultant covariance matrices are not factor models. Based on empirical backtests, we compare the performance of these machine learning risk models to other constructions, including statistical risk mode…
Geometric models improve feature extraction and equivariance in image generation.
problem Improving feature extraction at multiscale levels and reducing network complexity.
method Proposes a geometric generative model based on morphological PDEs and GANs, incorporating equivariance for geometric interpretability.
result Preliminary results show GM-GAN outperforms classical GANs on MNIST data.
An evolutionary algorithm (EA) is developed as an alternative to the EM algorithm for parameter estimation in model-based clustering. This EA facilitates a different search of the fitness landscape, i.e., the likelihood surface, utilizing both crossover and mutation. Furthermore, this EA represents an efficient approac…
Unified framework for policy improvement in RL with benefits in data efficiency and computation.
problem Improving data efficiency and computation in reinforcement learning for continuous control.
method Local, regularized policy improvement with tree search for continuous action spaces.
result Improves data efficiency and reduces wall-clock time in high-dimensional domains.
VMBPO optimizes model and policy jointly using variational lower-bound.
problem Data efficiency in RL with biased simulated data.
method Formulate variational objective function, use EM, iteratively improve model and policy.
result VMBPO is more sample-efficient and robust than model-free algorithms.
Model-based reinforcement learning (RL) has proven to be a data efficient approach for learning control tasks but is difficult to utilize in domains with complex observations such as images. In this paper, we present a method for learning representations that are suitable for iterative model-based policy improvement, e…
A framework evaluates synthetic tabular data quality objectively.
problem Lack of an objective interpretation of tabular data metrics.
method Proposes a single mathematical objective for synthetic tabular data distribution, structurally decomposes it, and unifies existing metrics.
result Synthesizers that represent tabular structure outperform other methods, especially on smaller datasets.
Unified Latent Dynamics unifies model-free and model-based reinforcement learning.
problem Combining the efficiency of model-free methods with the representational strengths of model-based approaches.
method Embedding state-action pairs into a latent space where the true value function is approximately linear, using synchronized updates of encoder, value, and policy networks.
result ULD achieves cross-domain competence with minimal tuning and a fraction of the parameter footprint.