Model-based Reinforcement Learning

195 papers with code • 0 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?

Libraries

Use these libraries to find Model-based Reinforcement Learning models and implementations

Datasets


Model-based Reinforcement Learning for Parameterized Action Spaces

valarzz/model-based-reinforcement-learning-for-parameterized-action-spaces 3 Apr 2024

We propose a novel model-based reinforcement learning algorithm -- Dynamics Learning and predictive control with Parameterized Actions (DLPA) -- for Parameterized Action Markov Decision Processes (PAMDPs).

5
03 Apr 2024

Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards

yasinsonmez/symmetry-cs285 27 Mar 2024

Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy.

0
27 Mar 2024

Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy Search

probabilistic-ml/pirl 23 Mar 2024

We compare trajectory sampling with density-based approximation for uncertainty propagation using three different probabilistic world models; Gaussian processes, Bayesian neural networks, and DGCNs.

2
23 Mar 2024

SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning

nzolman/sindy-rl 14 Mar 2024

Deep reinforcement learning (DRL) has shown significant promise for uncovering sophisticated control policies that interact in environments with complicated dynamics, such as stabilizing the magnetohydrodynamics of a tokamak fusion reactor or minimizing the drag force exerted on an object in a fluid flow.

10
14 Mar 2024

Mastering Memory Tasks with World Models

chandar-lab/Recall2Imagine 7 Mar 2024

Through a diverse set of illustrative tasks, we systematically demonstrate that R2I not only establishes a new state-of-the-art for challenging memory and credit assignment RL tasks, such as BSuite and POPGym, but also showcases superhuman performance in the complex memory domain of Memory Maze.

38
07 Mar 2024

Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control

ryeii/veri_hvac 29 Feb 2024

We found that the high dimensionality of the thermal dynamics model input hinders the efficiency of policy extraction.

2
29 Feb 2024

Model-based deep reinforcement learning for accelerated learning from flow simulations

janisgeise/mb_drl_for_accelerated_learning_from_cfd 26 Feb 2024

Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control system, provides a virtual testbed for safety-critical control applications, and allows to gain a deep understanding of the control mechanisms.

0
26 Feb 2024

The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning

anyasims/edge-of-reach 19 Feb 2024

The prevailing theoretical understanding is that this can then be viewed as online reinforcement learning in an approximate dynamics model, and any remaining gap is therefore assumed to be due to the imperfect dynamics model.

3
19 Feb 2024

A Distributional Analogue to the Successor Representation

jessefarebro/distributional-sr 13 Feb 2024

This paper contributes a new approach for distributional reinforcement learning which elucidates a clean separation of transition structure and reward in the learning process.

6
13 Feb 2024

Augmenting Replay in World Models for Continual Reinforcement Learning

cerenaut/wmar 30 Jan 2024

Also, the concept of replay comes from biological inspiration, where evidence suggests that replay is applied to a world model, which implies model-based RL -- and model-based RL should have benefits for continual RL, where it is possible to exploit knowledge independent of the policy.

0
30 Jan 2024