Active Reinforcement Learning for Robust Building Control

• URL: http://arxiv.org/abs/2312.10289v1
• Date: Sat, 16 Dec 2023 02:18:45 GMT
• Title: Active Reinforcement Learning for Robust Building Control
• Authors: Doseok Jang, Larry Yan, Lucas Spangher, Costas Spanos
• Abstract summary: Reinforcement learning (RL) is a powerful tool for optimal control that has found great success in Atari games, the game of Go, robotic control, and building optimization. Unsupervised environment design (UED) has been proposed as a solution to this problem, in which the agent trains in environments that have been specially selected to help it learn. We show that ActivePLR is able to outperform state-of-the-art UED algorithms in minimizing energy usage while maximizing occupant comfort in the setting of building control.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) is a powerful tool for optimal control that has found great success in Atari games, the game of Go, robotic control, and building optimization. RL is also very brittle; agents often overfit to their training environment and fail to generalize to new settings. Unsupervised environment design (UED) has been proposed as a solution to this problem, in which the agent trains in environments that have been specially selected to help it learn. Previous UED algorithms focus on trying to train an RL agent that generalizes across a large distribution of environments. This is not necessarily desirable when we wish to prioritize performance in one environment over others. In this work, we will be examining the setting of robust RL building control, where we wish to train an RL agent that prioritizes performing well in normal weather while still being robust to extreme weather conditions. We demonstrate a novel UED algorithm, ActivePLR, that uses uncertainty-aware neural network architectures to generate new training environments at the limit of the RL agent's ability while being able to prioritize performance in a desired base environment. We show that ActivePLR is able to outperform state-of-the-art UED algorithms in minimizing energy usage while maximizing occupant comfort in the setting of building control.

Related papers

• Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks [3.479490713357225]
  We procedurally generate tens of millions of 2D physics-based tasks and use these to train a general reinforcement learning (RL) agent for physical control. Kinetix is an open-ended space of physics-based RL environments that can represent tasks ranging from robotic locomotion and grasping to video games and classic RL environments. Our trained agent exhibits strong physical reasoning capabilities, being able to zero-shot solve unseen human-designed environments.
  arXiv  Detail & Related papers  (2024-10-30T16:59:41Z)
• A Benchmark Environment for Offline Reinforcement Learning in Racing Games [54.83171948184851]
  Offline Reinforcement Learning (ORL) is a promising approach to reduce the high sample complexity of traditional Reinforcement Learning (RL) This paper introduces OfflineMania, a novel environment for ORL research. It is inspired by the iconic TrackMania series and developed using the Unity 3D game engine.
  arXiv  Detail & Related papers  (2024-07-12T16:44:03Z)
• Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity [21.40849085315057]
  We study the effectiveness of R2N in the Extremely Noisy Environment setting, an RL problem setting where up to 95% of the state features are irrelevant distractions. In experiments with a simulated teacher, we demonstrate that R2N can adapt the sparse connectivity of its neural networks to focus on task-relevant features.
  arXiv  Detail & Related papers  (2024-06-10T17:31:07Z)
• Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning [66.10854214036605]
  A central question in robotics is how to design a control system for an agile mobile robot. We show that a neural network controller trained with reinforcement learning (RL) outperformed optimal control (OC) methods in this setting. Our findings allowed us to push an agile drone to its maximum performance, achieving a peak acceleration greater than 12 times the gravitational acceleration and a peak velocity of 108 kilometers per hour.
  arXiv  Detail & Related papers  (2023-10-17T02:40:27Z)
• A Multiplicative Value Function for Safe and Efficient Reinforcement Learning [131.96501469927733]
  We propose a safe model-free RL algorithm with a novel multiplicative value function consisting of a safety critic and a reward critic. The safety critic predicts the probability of constraint violation and discounts the reward critic that only estimates constraint-free returns. We evaluate our method in four safety-focused environments, including classical RL benchmarks augmented with safety constraints and robot navigation tasks with images and raw Lidar scans as observations.
  arXiv  Detail & Related papers  (2023-03-07T18:29:15Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Low Emission Building Control with Zero-Shot Reinforcement Learning [70.70479436076238]
  Control via Reinforcement Learning (RL) has been shown to significantly improve building energy efficiency. We show it is possible to obtain emission-reducing policies without a priori--a paradigm we call zero-shot building control.
  arXiv  Detail & Related papers  (2022-08-12T17:13:25Z)
• Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control [0.0]
  We investigate the performance of DRL agents compared to the theoretically optimal solution. Our results hint that DRL agents not only clearly outperform conventional rule-based controllers, they furthermore attain near-optimal performance.
  arXiv  Detail & Related papers  (2022-03-10T15:41:29Z)
• Curriculum Based Reinforcement Learning of Grid Topology Controllers to Prevent Thermal Cascading [0.19116784879310028]
  This paper describes how domain knowledge of power system operators can be integrated into reinforcement learning frameworks. A curriculum-based approach with reward tuning is incorporated into the training procedure by modifying the environment. A parallel training approach on multiple scenarios is employed to avoid biasing the agent to a few scenarios and make it robust to the natural variability in grid operations.
  arXiv  Detail & Related papers  (2021-12-18T20:32:05Z)
• Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training [71.7750435554693]
  We show that several state-of-the-art RL agents proposed for power system control are vulnerable to adversarial attacks. Specifically, we use an adversary Markov Decision Process to learn an attack policy, and demonstrate the potency of our attack. We propose to use adversarial training to increase the robustness of RL agent against attacks and avoid infeasible operational decisions.
  arXiv  Detail & Related papers  (2021-10-18T00:50:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.