arXiv research

M3PO improves model-based meta-RL with theoretical guarantees.

Introduces LoCA regret to evaluate model-based RL methods.

Unified framework for model-based RL with sample complexity guarantees.

FOCUS improves offline RL by incorporating causal structure into world-models.

This work explores representation complexity in RL paradigms, revealing model-based RL as the easiest task.

Survey of integrating planning and learning in model-based reinforcement learning.

MOPO optimizes offline RL by penalizing dynamics uncertainty.

Optimistic RL algorithms are simplified for deep RL with competitive performance.

MOReL learns offline RL policies using pessimistic MDPs.

RL agent outperforms model-based approach in detecting price manipulation.

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…

This study tackles adversarial corruption in model-based reinforcement learning.

Clarifies model-based RL's theoretical issues and counterexamples for popular losses.

State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered experience. In this paper, we focus on model-based RL in the finite-state finite-horizon…

PriMORL trains private RL policies on offline data.

Unified framework for policy improvement in RL with benefits in data efficiency and computation.

Python module for RL trading in limit order books.

MoMA improves model-based RL by using unrestricted policy classes.

RH-UCRL combines pessimism and optimism for robust RL.

New RL method handles diverse human operator data.

New RL algorithm minimizes distributional learning error.

The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples. Although using many samples tends to improve the accuracy of policy learning, c…

Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper introduces a novel algorithmic framework for designing and analyzing model-based RL algo…

New algorithms achieve uniform-PAC guarantees for RL with bounded eluder dimension.

RL in MFGs is as hard as solving many single-agent RL problems.

VMBPO optimizes model and policy jointly using variational lower-bound.

In this paper we study how to learn stochastic, multimodal transition dynamics in reinforcement learning (RL) tasks. We focus on evaluating transition function estimation, while we defer planning over this model to future work. Stochasticity is a fundamental property of many task environments. However, discriminative f…

Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for such tasks: model-free or model-based. Each of these approaches has limitations.…

A method for learning a context latent vector to improve generalization in model-based RL.

Efficient RL algorithm for multinomial logistic MDPs with provable guarantees.

This study assesses model influence on RL algorithm performance.

We study the sample complexity of model-based reinforcement learning (henceforth RL) in general contextual decision processes that require strategic exploration to find a near-optimal policy. We design new algorithms for RL with a generic model class and analyze their statistical properties. Our algorithms have sample …

New RL framework models continuous-time dynamics using neural ODEs.

This work tackles model-based RL by optimizing state-action queries to learn policies with minimal data.

New hybrid RL algorithm outperforms model-free and model-based methods.

This paper optimizes model-based RL for two-player zero-sum games with near-optimal sample complexity.

Improves sample efficiency in RL by matching model-based gradients.

Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a challenging problem. Here, we design a deep reinforcement learning (RL) architec…

Survey of methods for learning from observation without requiring expert actions.

New method accelerates MBRL by 10x for complex quadrotor tasks.

Combines model-based and model-free RL for better financial market performance.

Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction challenging. We address these issues with a new model-based reinforcement learnin…

Sepsis is a dangerous condition that is a leading cause of patient mortality. Treating sepsis is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. In this work, we explore the use of continuous state-space mode…

Some of the most important tasks take place in environments which lack cheap and perfect simulators, thus hampering the application of model-free reinforcement learning (RL). While model-based RL aims to learn a dynamics model, in a more general case the learner does not know a priori what the action space is. Here we …

This paper tackles distribution shift in model-based offline RL, proposing a shifts-aware reward method.

New RL algorithm reduces regret in finite-horizon episodic tasks.

Self-consistent models improve reinforcement learning by aligning predictions with future values.

A new framework reduces RL sample complexity for complex MDPs.