A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
Learning-based Model Predictive Control for Safe Exploration
[article]
2018
arXiv
pre-print
Preserved Fulltext
Other Versions
In this paper, we present a learning-based model predictive control scheme that can provide provable high-probability safety guarantees. ...
In our experiments, we show that the resulting algorithm can be used to safely and efficiently explore and learn about dynamic systems. ...
Another area that has considered learning for control is model-based RL. ...
arXiv:1803.08287v3
fatcat:7v6bk4w7wzb67cv4ll4wsix32a
Learning-Based Model Predictive Control for Safe Exploration
2018
2018 IEEE Conference on Decision and Control (CDC)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We combine a provably safe learning-based MPC scheme that allows for input-dependent uncertainties with techniques from model-based RL to solve tasks with only limited prior knowledge. ...
In this paper, we attempt to bridge the gap between learning-based techniques that are scalable and highly autonomous but often unsafe and robust control techniques, which have a solid theoretical foundation ...
Reinforcement learning objective and MPC scheme We require an objective function that jointly encourages exploration and finding a good control strategy based on our current statistical model. ...
doi:10.1109/cdc.2018.8619572
dblp:conf/cdc/KollerBT018
fatcat:omofexgb6vbzrnuluspinjmnmu
Towards Safe Reinforcement-Learning in Industrial Grid-Warehousing
2020
Information Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
On the other hand, model-based reinforcement learning tries to encode environment transition dynamics into a predictive model. ...
The key contributions of this paper are summarized as follows: DVAE, a predictive model for n-state predictions, safety constraints using a constrained MDP scheme, safe exploration through risk-directed ...
Safe predictive model In model-based reinforcement learning, the goal is to efficiently learn a predictive model that accurately learns the environment dynamics to predict future states given the current ...
doi:10.1016/j.ins.2020.06.010
fatcat:kzm4owdbzfhvvnwv653dvxm47u
Safe Interactive Model-Based Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The learned safe set and model can also be used for safe exploration, i.e., to collect data within the safe invariant set, for which a simple one-step MPC is proposed. ...
This paper introduces Safe Interactive Model Based Learning (SiMBL), a framework to refine an existing controller and a system model while operating on the real environment. ...
We are also grateful to Felix Berkenkamp for the support given while experimenting with their safe learning tools. ...
arXiv:1911.06556v2
fatcat:fx22zrnlhfdsxfqen66utzk3zi
Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2108.06266v1 fatcat:szah35r4tbf6vdnatxfeewwt6a
The last half-decade has seen a steep rise in the number of contributions on safe learning methods for real-world robotic deployments from both the control and reinforcement learning communities. ...
Our review includes: learning-based control approaches that safely improve performance by learning the uncertain dynamics, reinforcement learning approaches that encourage safety or robustness, and methods ...
Previous review works focused on specific techniques-for example, learning-based model predictive control (MPC) (7) , iterative learning control (ILC) (8, 9) , model-based RL (10) , data-efficient policy ...
arXiv:2108.06266v2
fatcat:gbbe3qyatfgelgzhqzglecr5qm
LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2107.04775v1 fatcat:cfr6jy3vyngvvidbpyxjcui3wa
A promising strategy for learning in dynamically uncertain environments is requiring that the agent can robustly return to learned safe sets, where task success (and therefore safety) can be guaranteed ...
We present a novel continuous representation for safe sets by framing it as a binary classification problem in a learned latent space, which flexibly scales to image observations. ...
These methods learn predictive models over either images or a learned latent space, which are then used by model predictive control (MPC) to optimize image-based task costs. ...
arXiv:2107.04775v2
fatcat:kmhxtsvfu5hojdrwff2qk6x7he
Improving Safety in Reinforcement Learning Using Model-Based Architectures and Human Intervention
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We present a hybrid method for reducing the human intervention time by combining model-based approaches and training a supervised learner to improve sample efficiency while also ensuring safety. ...
Currently, Safe RL systems use human oversight during training and exploration in order to make sure the RL agent does not go into a catastrophic state. ...
Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein. ...
arXiv:1903.09328v1
fatcat:b2zsyziyprc7rgiukw4durauzu
Risk Sensitive Model-Based Reinforcement Learning using Uncertainty Guided Planning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Identifying uncertainty and taking mitigating actions is crucial for safe and trustworthy reinforcement learning agents, especially when deployed in high-risk environments. ...
In this paper, risk sensitivity is promoted in a model-based reinforcement learning algorithm by exploiting the ability of a bootstrap ensemble of dynamics models to estimate environment epistemic uncertainty ...
Funding in direct support of this work: EPSRC Centre for Doctoral Training Studentship (EP/S022937/1). The authors declare no conflicts of interest. ...
arXiv:2111.04972v1
fatcat:4d2y4uqm5zcl7eelnddkrztx3m
Safe Zero-Shot Model-Based Learning and Control: A Wasserstein Distributionally Robust Approach
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We identify and focus on scenarios of learning and controlling a system from scratch, starting with a randomly initialized model based on the strongest possible limitations on our prior knowledge of the ...
This paper labels this scenario as a "zero-shot" control problem, based on popular zero-shot transfer problems in machine learning. ...
Safe Zero-Shot Model-Based Learning and Control: A Wasserstein Distributionally Robust Approach Aaron Kandel and Scott J. ...
arXiv:2004.00759v3
fatcat:znxsbd35azdlld44japrbp5xuq
Safe Reinforcement Learning on Autonomous Vehicles
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We investigate how prediction provides a general and intuitive framework to constraint exploration, and show how it can be used to safely learn intersection handling behaviors on an autonomous vehicle. ...
Recent work in safe reinforcement learning uses idealized models to achieve their guarantees, but these models do not easily accommodate the stochasticity or high-dimensionality of real world systems. ...
PREDICTION We propose using prediction models to mask unsafe actions from the agent, and then allow the agent to freely explore the safe state space using traditional RL techniques. ...
arXiv:1910.00399v1
fatcat:esa66f5pxzfgngpbw5kd7aq3eq
Text/Conference Paper
2019
Jahrestagung der Gesellschaft für Informatik
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The proposed approach generates data appropriate for time series model learning, i.e. input and output trajectories, by dynamically exploring the input space. ...
Learning time-series models is useful for many applications, such as simulation and forecasting. ...
In safe active learning, [20] proposes a method for safe exploration based on the GP variance for stationary, i.e. pointwise, measurements. ...
doi:10.18420/inf2019_44
dblp:conf/gi/ZimmerMN19
fatcat:sb5yhqxwlbcf3i7t3jhlbgovte
Safe Reinforcement Learning with Chance-constrained Model Predictive Control
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We address the challenge of safe RL by coupling a safety guide based on model predictive control (MPC) with a modified policy gradient framework in a linear setting with continuous actions. ...
We show theoretically that this penalty allows for a provably safe optimal base policy and illustrate our method with a simulated linearized quadrotor experiment. ...
Model Predictive Control Model predictive control is a purely optimization-based planning framework. ...
arXiv:2112.13941v2
fatcat:3rbp3kk7iveefkjpvtzs4thj7u
Reinforcement learning based algorithm with Safety Handling and Risk Perception
2016
2016 IEEE Symposium Series on Computational Intelligence (SSCI)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
This paper presents the setup and the results of a reinforcement learning problem utilizing Q-learning and a Safety Handling Exploration with Risk Perception Algorithm (SHERPA) for safe exploration in ...
The agent has to explore its environment safely and must learn the optimal action for a given situation from the feedback received from the environment. ...
[6] propose a Qlearning based navigation algorithm for autonomous systems that shows good performance and learning for safe navigation in an unknown environment. ...
doi:10.1109/ssci.2016.7849367
dblp:conf/ssci/ShyamsundarMK16
fatcat:4rewatc4hvchlggqlxggy4dq7e
Safe Reinforcement Learning for Legged Locomotion
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Model-free reinforcement learning provides promising tools to tackle this challenge. However, a major bottleneck of applying model-free reinforcement learning in real world is safety. ...
Designing control policies for legged locomotion is complex due to the under-actuated and non-continuous robot dynamics. ...
Ramadge for the helpful discussion and members of Google Research for helpful discussion and support of the experiments. ...
arXiv:2203.02638v1
fatcat:er3ctxha4vcotjwxtgfpeyqpxi
A predictive safety filter for learning-based control of constrained nonlinear dynamical systems
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Safety is thereby established by a continuously updated safety policy, which is based on a model predictive control formulation using a data-driven system model and considering state and input dependent ...
The predictive safety filter receives the proposed control input and decides, based on the current system state, if it can be safely applied to the real system, or if it has to be modified otherwise. ...
Learning-based model predictive control: Originating from concepts in robust model predictive control (MPC), extensions of MPC schemes to safe learning-based methods have been proposed, see e.g. ...
arXiv:1812.05506v4
fatcat:chelnjgrrjgpnkvfjsoxarygae
« Previous
Showing results 1 — 15 out of 180,910 results