Research
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.

168,932 papers · 148 categories

Trend · papers per month

6141,2281,8412,455 · Jun 202019922001200920172026
48 results for Reinforcement Learning for POMDP

This research develops an efficient reinforcement learning method for undercomplete POMDPs.

problem Learning undercomplete Partially Observable Markov Decision Processes (POMDPs) is computationally hard.
method OOM-UCB algorithm for episodic finite undercomplete POMDPs.
result Achieves optimal sample complexity of ildeO(1/ε2) ilde{\mathcal{O}}(1/\varepsilon^2) for finding an ε\varepsilon-optimal policy.

PS4POMDPs algorithm simplifies online learning for episodic POMDPs with unknown models.

problem Learning in POMDPs is harder than in MDPs; online learning is especially challenging.
method Posterior Sampling-based reinforcement learning algorithm (PS4POMDPs)
result Bayesian regret scales as √number of episodes and is polynomial in other parameters.

Study off-policy evaluation in partially observable environments, reducing bias and errors.

problem Bias and large errors in off-policy evaluation for partially observable environments.
method Defined and solved off-policy evaluation for POMDPs, introduced Decoupled POMDP model.
result Demonstrated and compared off-policy evaluation methods, showing benefits of new approach.

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging…

2016-02-25abs ↗pdf ↗

ETC learns minimal representations for reinforcement learning in POMDPs.

problem Sample complexity challenges in reinforcement learning for POMDPs.
method ETC learns low-dimensional features and embeddings at two levels, optimizing policy.
result ETC achieves polynomial sample complexity for POMDPs with low-rank transition kernels.

A new reinforcement learning method for medical decisions with limited data.

problem Learning high-performing policies from partially observed data in healthcare.
method Optimization objective that combines policy and generative model quality, suitable for batch off-policy settings.
result Demonstrated improved performance on synthetic and medical decision-making problems.

Bayesian reinforcement learning (BRL) encodes prior knowledge of the world in a model and represents uncertainty in model parameters by maintaining a probability distribution over them. This paper presents Monte Carlo BRL (MC-BRL), a simple and general approach to BRL. MC-BRL samples a priori a finite set of hypotheses…

2012-06-27abs ↗pdf ↗

RL struggles with generalization due to implicit partial observability.

problem Generalization in RL is difficult due to implicit partial observability.
method Re-cast RL problem as solving epistemic POMDPs and propose ensemble-based techniques.
result Simple ensemble-based technique achieves significant generalization gains.

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 QQ-function, deterministic latent transitions, gap assumption.
result Computationally and statistically efficient algorithm for exact optimal policy.

This paper establishes strong lower bounds for learning in revealing POMDPs.

problem Understanding the fundamental limits of reinforcement learning in revealing partially observable Markov Decision Processes (POMDPs).
method Develops strong PAC and regret lower bounds for learning in revealing POMDPs using multi-step revealing POMDPs as a case study.
result Strong polynomial lower bounds for learning in revealing POMDPs, achieving significantly smaller gaps against current upper bounds.

New method learns belief representations for GAIL in POMDPs.

problem Imitation learning in partially observable Markov decision processes (POMDPs).
method Joint learning of belief module and policy with task-aware imitation loss and belief regularization.
result Our BMIL approach outperforms GAIL and task-agnostic belief learning.

Study efficient reinforcement learning for partially observed systems with linear structure.

problem Efficient reinforcement learning for partially observed Markov decision processes with linear structure.
method Proposes OP-TENET algorithm using a Bellman operator with finite memory, adversarial integral equation, and optimistic exploration.
result Achieves ε-optimal policy within O(1/ε^2) episodes with polynomial sample complexity in intrinsic dimension.

New algorithm improves reinforcement learning from partial observations.

problem Inferior performance of algorithms in real-world reinforcement learning due to partial observability.
method Representation-based approach to POMDPs, leading to a tractable algorithm.
result Empirically demonstrates superior performance with partial observations.

DPFRL uses particle filters for decision making with complex visual observations.

problem Decision making with partial complex visual observations.
method Discriminative Particle Filter Reinforcement Learning (DPFRL) with a differentiable particle filter in the neural network policy.
result DPFRL outperforms state-of-the-art POMDP RL models in complex visual observation tasks.

We present a data-efficient reinforcement learning algorithm resistant to observation noise. Our method extends the highly data-efficient PILCO algorithm (Deisenroth & Rasmussen, 2011) into partially observed Markov decision processes (POMDPs) by considering the filtering process during policy evaluation. PILCO conduct…

2016-02-08abs ↗pdf ↗

PRL improves off-policy evaluation in partially observed MDPs.

problem Confounding and bias in offline reinforcement learning with unobserved state factors.
method Extends proximal causal inference to POMDPs, identifying and estimating target policy value.
result Semiparametrically efficient estimators for PRL in partially observed MDPs.

This work tackles maintenance planning with deep reinforcement learning under uncertainty.

problem Optimizing inspection and maintenance policies in deteriorating environments with incomplete information and constraints.
method Joint framework of constrained POMDPs and multi-agent DRL addressing challenges of state/action space, history, uncertainty, and constraints.
result The proposed framework outperforms existing methods in resource and risk-aware decision-making.

This paper advances sample-efficient learning for partially observable RL by introducing B-stability and new algorithms.

problem Hard sample complexity for learning near-optimal policies in partially observable RL.
method Proposes B-stability as a unified structural condition and develops new algorithms for sample-efficient learning.
result Any B-stable PSR can be learned with polynomial samples, improving over current best complexities.

Many interesting real world domains involve reinforcement learning (RL) in partially observable environments. Efficient learning in such domains is important, but existing sample complexity bounds for partially observable RL are at least exponential in the episode length. We give, to our knowledge, the first partially …

2016-05-25abs ↗pdf ↗

Reinforcement Learning improves personalized dialogue systems.

problem Personalized dialogue systems that generalize across users.
method Two RL-based approaches: single learner with user context features, and learner per context segmentation.
result RL methods outperform handcrafted systems in financial product recommendation.

Paper solves POMDPs in continuous time and discrete spaces.

problem Optimal decision making in discrete state and action space systems under partial observability.
method Combining optimal filtering theory and deep learning to solve a Hamilton-Jacobi-Bellman equation.
result Derives a mathematical description and solution approach for continuous-time POMDPs.

OMLE combines optimism and MLE for efficient sequential decision making.

problem Efficiently solving sequential decision making problems, especially in partially observable settings.
method Combines optimism for exploration and maximum likelihood estimation for model learning.
result OMLE learns near-optimal policies for a wide range of sequential decision making problems.

This paper optimizes attacks on reinforcement learning policies, reducing their effectiveness.

problem Optimizing adversarial attacks on reinforcement learning policies to minimize rewards.
method Designing optimal attacks for both white-box and black-box scenarios using Markov Decision Processes and Reinforcement Learning.
result Optimal attacks can reduce the effectiveness of reinforcement learning policies, especially for smooth policies.

The paper proposes an algorithm to learn causal state representations for partially observable environments.

problem Learning task-agnostic state abstractions in partially observable environments.
method The approach involves learning approximate causal state representations from RNNs trained to predict observations given the history.
result The learned state representations are useful for efficient policy learning in reinforcement learning problems with rich observation spaces.

A framework for multi-agent communication over noisy channels in reinforcement learning.

problem Effective communication between multiple agents in a noisy environment.
method A novel multi-agent partially observable Markov decision process (MA-POMDP) framework considering noisy communication channels.
result Jointly learned policies outperform separate learning of communication and decision making.

New algorithm tackles confounding in offline RL for partially observable MDPs.

problem Confounding in offline reinforcement learning for partially observable MDPs.
method P3O algorithm using proximal causal inference and pessimistic confidence regions.
result Achieves n1/2n^{-1/2}-suboptimality for offline RL in POMDPs with confounded data.

Deep RL for dynamic pricing of express lanes considers multiple origins, destinations, and access locations.

problem Dynamic pricing of express lanes with multiple access points and traveler heterogeneity.
method Formulated as a POMDP, uses policy gradient methods and neural networks to determine stochastic tolls.
result Deep RL outperforms traditional methods in maximizing revenue and minimizing travel time.

New algorithms learn POMDPs efficiently with hindsight observability.

problem Hardness of learning in POMDPs due to partial observability.
method Hindsight Observable Markov Decision Process (HOMDP) and new algorithms for tabular and function approximation settings.
result Sample-efficient learning in POMDPs with optimal dependence on latent state and observation cardinalities.