arXiv research

Hybrid controller combines model-based and policy-based reinforcement learning.

Simple model-based reinforcement learning outperforms model-free methods in complex tasks.

Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representational limitations in making assumptions about the world dynamics and model errors inevitable in complex domains. However, they require a lo…

Adapts model-based advice to stabilize black-box policies for nonlinear control.

Unified reinforcement learning methods using hybrid inference.

This paper compares model-based and model-free control methods using neural networks.

Model based predictions of future trajectories of a dynamical system often suffer from inaccuracies, forcing model based control algorithms to re-plan often, thus being computationally expensive, suboptimal and not reliable. In this work, we propose a model agnostic method for estimating the uncertainty of a model?s pr…

New model learning objective improves continuous control tasks.

Continuous-time MBRL framework tackles control systems with Bayesian ODEs.

Deep reinforcement learning controls drones without model knowledge.

The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous control tasks, we study the sample complexity of popular model-based and model-free algorithms on the Linear Quadratic Regulator (LQR). We show…

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

Improves data efficiency in multi-agent control tasks using model-based reinforcement learning.

New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.

Proposes a new reinforcement learning method to improve agent performance in control tasks.

PID control architectures are widely used in industrial applications. Despite their low number of open parameters, tuning multiple, coupled PID controllers can become tedious in practice. In this paper, we extend PILCO, a model-based policy search framework, to automatically tune multivariate PID controllers purely bas…

MAGE optimizes policies using action gradients from model-based learning.

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

Model-Based Offline Planning (MBOP) learns models from offline data to control systems directly.

A framework for data-driven decision-making in infectious disease control.

Paper proposes CARL for better control in RL from sensory data.

Model-based reinforcement learning has the potential to be more sample efficient than model-free approaches. However, existing model-based methods are vulnerable to model bias, which leads to poor generalization and asymptotic performance compared to model-free counterparts. In addition, they are typically based on the…

Unified Latent Dynamics unifies model-free and model-based reinforcement learning.

New model-based methods adapt pre-trained policies to unseen environments efficiently.

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

Proposes H-UCRL for efficient model-based RL with sublinear regret.

Digital twins improve single-arm trials by providing robust treatment effect estimates.

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

FLEX optimizes exploration for nonlinear systems with minimal data.

This paper improves robot grasping by integrating meta-control and latent-space imagination.

Minimum attention improves reinforcement learning performance in high-dimensional dynamics.

A framework schedules hyperparameters for model-based reinforcement learning, improving performance.

Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of c…

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

Combining causality, control, and reinforcement learning for system control.

PriMORL trains private RL policies on offline data.

Reinforcement learning algorithms are gaining popularity in fields in which optimal scheduling is important, and oncology is not an exception. The complex and uncertain dynamics of cancer limit the performance of traditional model-based scheduling strategies like Optimal Control. Motivated by the recent success of mode…

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…

Model-free approaches for reinforcement learning (RL) and continuous control find policies based only on past states and rewards, without fitting a model of the system dynamics. They are appealing as they are general purpose and easy to implement; however, they also come with fewer theoretical guarantees than model-bas…

We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms so as to improve the exploration of the state-space, and substantially reduce learning times by leveraging some limited knowledge of the plant encoded into a tutoring model-based control strategy. …

DyNODE uses neural ODEs to model system dynamics in continuous control tasks.

Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning (RL) approaches typically require many interactions with the system t…

We show LLMs can be locally linear, enabling better control of activations.

Model-based reinforcement learning has been empirically demonstrated as a successful strategy to improve sample efficiency. In particular, Dyna is an elegant model-based architecture integrating learning and planning that provides huge flexibility of using a model. One of the most important components in Dyna is called…

Model learns and plans in real-time under constraints for robotic systems.

Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generat…

Neural Laplace Control tackles offline RL for continuous-time delayed systems with irregular observations.

Curious Replay improves model-based reinforcement learning agents' adaptability.