Method learns latent states from rich observations to improve RL exploration.
problem Improving RL performance with rich observations and latent states.
method Estimates latent states from observations through regression and clustering, providing finite-sample guarantees.
result Exponential improvement over Q-learning with naïve exploration. This research improves dynamical systems understanding by identifying latent states and their nonlinear transitions.
problem Previous work on dynamical systems could not identify nonlinear transition dynamics, leading to unreliable predictions.
method Proposes a state-space modeling framework using variational auto-encoders to identify latent states and their nonlinear transition functions.
result Demonstrates high accuracy in recovering latent state dynamics and future prediction accuracy.
New model captures state-dependent variability in partially observed systems.
problem Structured stochasticity not captured by constant-variance models.
method State-coupled stochastic volatility framework with particle expectation-maximization.
result Model consistently reduces recovery bias under partial observation.
Study reveals latent state computation in stochastic volatility models.
problem Understanding latent stochastic dynamics in noisy, partially observed observations.
method Multivariate stochastic volatility setting, controlled experiments on various architectures.
result Evidence of a two-stage computation: latent state encoding and output head mapping.
Paper models non-linear dynamics from time series data.
problem Modeling non-linear dynamical systems from time series data.
method Introduces latent state modeling and a novel alternating minimization algorithm.
result LaNoLem achieves competitive performance in dynamics estimation and prediction.
New 2D maps improve image captioning models.
problem Captions generated by RNNs are often poor.
method Used 2D maps instead of vectors to represent latent states.
result 2D maps lead to better captioning performance.
Advantage amplification helps RL in slow-evolving latent-state environments.
problem Challenges in reinforcement learning for long-horizon latent-state environments.
method Temporal abstraction and aggregation methods to overcome belief state error and small action advantage.
result Proven advantage amplification in settings with slowly evolving latent states.
Improved DSSMs for easier interpretable latent variables.
problem Complex and hard-to-interpret latent variables in DSSMs.
method Simplified predictive decoder and shrinkage priors.
result Interpretable latent variables improve forecasting performance.
New algorithms tackle latent bandit problems with lower regret.
problem Learning optimal actions in a latent state setting.
method General algorithms based on UCBs and Thompson sampling, aware of model uncertainty.
result Our methods have lower regret than classic bandit policies when latent states are fewer than actions.
This paper tackles belief-state selection in simulators with latent states.
problem Selecting among approximate belief-state samplers for simulators with latent variables.
method Reduces belief-state selection to conditional distribution selection, develops algorithms and analyses.
result Different formulations of belief-state selection have varying guarantees under different roll-out methods.
Adversarial attacks on probabilistic state-space models affect latent state and policy decisions.
problem Robust reinforcement learning under adversarial observability.
method Analyzing adversarial attacks on linear probabilistic state-space models.
result Demonstrating the influence of adversarial observations on latent state and policy decisions.
DeepMDP simplifies complex observations into continuous latent states.
problem Learning from high-dimensional observations in reinforcement learning.
method Trains a DeepMDP model that predicts rewards and next latent states.
result Optimization of DeepMDP objectives ensures quality of latent space and environment model.
Combines deep state space models with diffusion models for better forecasting and capturing latent dynamics
problem Forecasting and capturing latent dynamics in time series
method DDSSM: Diffusion-driven state space model
result Empirically outperforms state-of-the-art deep SSM
Efficient RL in large POMDPs with latent determinism and embeddings.
problem Efficient reinforcement learning in large-scale POMDPs with latent states and observations.
method Conditional Hilbert space embeddings, linear optimal Q-function, deterministic latent transitions, gap assumption. result Computationally and statistically efficient algorithm for exact optimal policy.
Improved exploration in RL with latent state marginalization.
problem Complexity of deep probabilistic models limits their practical use in reinforcement learning.
method Adopting latent variable policies within the MaxEnt framework, with low-cost marginalization of latent states.
result Effective marginalization leads to better exploration and more robust training.
Paper introduces OMD for ordered state transitions in SSMs.
problem Modeling ordered latent states in dynamic systems.
method Ordered Matrix Dirichlet (OMD) prior over ordered stochastic matrices.
result OMD models recover interpretable ordered latent structure without sacrificing predictive performance.
A new model for time series using discrete latent states.
problem Efficiently modeling time series data with discrete latent states.
method A Markov chain-based model for training high-dimensional discrete latent data.
result Improved performance on time series datasets.
AC-State discovers minimal latent state for control.
problem Discover minimal latent state from sensory information.
method Multi-step inverse model with information bottleneck.
result Guaranteed discovery of control-endogenous latent states.
Proposes learning latent reward model for planning from rewards.
problem Planning in high-dimensional state spaces with limited reward information.
method Directly learns a latent dynamics model from rewards, planning in latent state-space.
result Successfully learns accurate latent reward prediction model, achieving strong performance and high sample efficiency.
We describe a Markov latent state space (MLSS) model, where the latent state distribution is a decaying mixture over multiple past states. We present a simple sampling algorithm that allows to approximate such high-order MLSS with fixed time and memory costs.
Paper proposes method for optimal control of unknown systems with latent states.
problem Jointly estimating dynamics and latent states in systems with unmeasurable states.
method Combination of particle Markov chain Monte Carlo methods and scenario theory.
result Probabilistic performance guarantees for optimal input trajectories.
Auto-regressive models learn latent states from partially observed linear dynamical systems.
problem Understanding how auto-regressive models learn latent representations from partially observed linear dynamical systems.
method Empirical risk minimization on partially observed linear dynamical systems.
result Two-layer linear auto-regressive models learn to approximate Kalman filtering, coinciding with optimal state estimates.
Unified approach for learning state representations from streaming data.
problem Learning reusable state representations from high-dimensional, non-stationary data.
method Unified mathematical formulation for learning latent relations, enabling flexible and principled shaping of latent space.
result Improved understanding and evaluation of existing unsupervised learning approaches.
HOMER learns latent states to explore rich environments efficiently.
problem Exploration in rich observation environments with unknown latent states.
method Interleaves representation learning and strategic exploration to identify kinematic states.
result Provably efficient exploration with polynomial sample complexity in latent states and time horizon.
New method improves robustness in partially observable domains by training against latent distribution shifts.
problem Challenges in robustness under latent distribution shift in partially observable reinforcement learning.
method Formalizes adversarial latent-initial-state POMDP, proves minimax principle, derives best-response inequalities.
result Reduces robustness gaps from 10.3 to 3.1 shots with targeted exposure to shifted latent distributions.
Generative models learn latent process to match target distributions.
problem Training flow-matching models with auxiliary stochastic dynamics.
method Introduces latent process generator matching, treating generative state as a deterministic image of a Markov process.
result Learn generator of a stochastic process with same marginal distributions.
LS4 models time-series with latent states, outperforming previous methods.
problem Learning sharp transitions in time-series data.
method State space ODE with convolutional representation to bypass hidden states.
result LS4 significantly outperforms previous models in various metrics.
Improved tracking and prediction of moving objects in visual data streams.
problem Tracking and predicting multiple moving objects in visual data streams.
method Disentangled latent state-space model with amortized variational Bayesian inference.
result Significantly improved long-term prediction and object decomposition in the presence of occlusions.
Active learning selects inputs for GPSSM to learn latent states.
problem Optimally learn latent states of a GPSSM through active selection of inputs.
method Use mutual information to select informative inputs; approximate mutual information for GPSSM.
result Effective active learning of GPSSM dynamics in physical systems.
New method infers hidden states in continuous-time phenomena better than traditional models.
problem Traditional HSMM's are limited to discrete time grids and cannot handle irregularly spaced data.
method Formulated integro-differential forward and backward equations for CTSMC's, introduced scalable Viterbi-type algorithm.
result Efficiently solved equations for posterior marginals and path estimates.
Latent variable models improve RL by facilitating efficient learning and exploration.
problem Improving sample efficiency in reinforcement learning.
method Representation view of latent variable models for state-action value functions, incorporating kernel embeddings and UCB exploration.
result Established sample complexity of the proposed approach in online and offline settings, demonstrated superior performance in benchmarks.
This paper introduces a new neural ODE model for continuous-time sequence generation.
problem Representing and predicting continuous-time sequences with high accuracy.
method A neural emission model and neural ODE define the latent state evolution, with an Energy-based model for prior distribution.
result The model outperforms existing methods in various tasks, including long-horizon predictions.
The paper characterizes brain states and transitions using functional MRI data.
problem Characterizing the dynamic reconfiguration of neural systems in brain states.
method Bayesian model-based characterization of latent brain states and posterior predictive discrepancy using the latent block model.
result The model detects transitions between latent brain states and identifies distinctive community patterns in task-fMRI data.
We decode latent states in Block MDPs and learn near-optimal policies.
problem Model estimation and reward-free learning in Block MDPs.
method Information-theoretical lower bound and efficient model estimation algorithm.
result Our algorithm approaches the information-theoretical limit for latent state decoding and converges to optimal policies.
Paper combines latent state space with CRF for improved autoregressive text generation.
problem Autoregressive models expose hidden state trajectory to biases.
method Combines latent state space model with CRF observation model.
result Improved performance on unconditional sentence generation compared to RNN and GAN baselines.
Paper learns hidden dynamics of partially observed chaotic systems for forecasting.
problem Data-driven identification of latent dynamical representations of partially-observed chaotic systems.
method Neural-network-based augmented state-space model for ODE representation learning.
result Reveals relevance to state-of-the-art approaches in short-term and long-term forecasting.
Improved MCMC for rare events in hidden Markov models.
problem Slow inference and prediction for rare latent states in hidden Markov models.
method Targeted sub-sampling (TASS) over-samples rare latent states, reducing variance in gradient estimation.
result Substantial gains in predictive and inferential accuracy on real and synthetic examples.
Latent-EnSF improves data assimilation for high-dimensional systems with sparse observations.
problem Challenges in high-dimensional, nonlinear Bayesian filtering with sparse observations.
method A novel data assimilation method using latent representations and a coupled VAE for efficient state encoding and reconstruction.
result Latent-EnSF outperforms traditional methods in accuracy, convergence, and efficiency for complex systems.
Algorithm finds latent structure in value functions for improved reinforcement learning.
problem Finding latent structure in value functions for efficient reinforcement learning.
method Proposes a practical algorithm using two posterior distributions over state abstractions and abstract-state values.
result Substantial performance gains in multi-task settings where tasks share a common, low-dimensional representation.
Agent decides when to measure latent states in RL to improve efficiency.
problem Costly state measurement in RL negatively affects future outcomes.
method Introduces AOMDP with measurement action, uses online RL and sequential Monte Carlo.
result Reduced uncertainty improves sample efficiency and policy value.
Generalizes bits back coding for time-series models with latent Markov structures.
problem Efficiently compressing time-series data with latent Markov structures.
method Extends bits back coding to time-series models with latent Markov structures, including HMMs and LGSSMs.
result Effective for small scale models, promising for larger scale settings like video compression.
We propose a nonparametric procedure to achieve fast inference in generative graphical models when the number of latent states is very large. The approach is based on iterative latent variable preselection, where we alternate between learning a 'selection function' to reveal the relevant latent variables, and use this …
Decodes neural activity to assess latent states in real-world driving tasks.
problem Understanding latent states during complex tasks in natural settings.
method Domain-generalized models trained on controlled lab paradigms applied to ecologically valid driving tasks.
result Changes in neural activity correlate with changes in behavior and task performance.
Latent FxLMS accelerates ANC by adapting along low-dimensional filter weights.
problem Improving active noise control with neural adaptive filters.
method Training an auto-encoder on filter coefficients, constraining weights to latent variables, and updating in latent space.
result Latent FxLMS converges in fewer steps with comparable error to standard FxLMS.
Algorithm improves imitation learning from visual data in partially observable environments.
problem Imitation learning from visual observations with missing expert actions and partial observability.
method Theoretical analysis and Latent Adversarial Imitation from Observations algorithm combining adversarial and latent representations.
result Latent Adversarial Imitation from Observations achieves state-of-the-art performance in high-dimensional robotic tasks.
Bayesian method synthesizes barrier certificates for unknown systems with latent states.
problem Certifying safety in systems with unknown dynamics and latent states.
method Bayesian inference with Metropolis-Hastings sampler and sum-of-squares program.
result Probabilistic validity of barrier certificates for unknown systems.
ROAD-EnKFs use learned low-dimensional models to improve state reconstruction and forecasting.
problem Reconstructing and forecasting states of unknown or expensive systems.
method Learned low-dimensional surrogate models and ensemble Kalman filter integration.
result ROAD-EnKFs achieve higher accuracy at lower computational cost than existing methods.
Recent advances in the estimation of deep directed graphical models and recurrent networks let us contribute to the removal of a blind spot in the area of probabilistc modelling of time series. The proposed methods i) can infer distributed latent state-space trajectories with nonlinear transitions, ii) scale to large d…