scholarly journals Training Champion-level Race Car Drivers Using Deep Reinforcement Learning

2021 ◽  
Author(s):  
Peter Wurman ◽  
Samuel Barrett ◽  
Kenta Kawamoto ◽  
James MacGlashan ◽  
Kaushik Subramanian ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
Learning Algorithm ◽  
Integrated Control ◽  
Extreme Case ◽  
Control Policy ◽  
Reward Function ◽  
Race Car ◽  
Model Free ◽  
Race Car Drivers

Abstract Many potential applications of artificial intelligence involve making real-time decisions in physical systems. Automobile racing represents an extreme case of real-time decision making in close proximity to other highly-skilled drivers while near the limits of vehicular control. Racing simulations, such as the PlayStation game Gran Turismo, faithfully reproduce the nonlinear control challenges of real race cars while also encapsulating the complex multi-agent interactions. We attack, and solve for the first time, the simulated racing challenge using model-free deep reinforcement learning. We introduce a novel reinforcement learning algorithm and enhance the learning process with mixed scenario training to encourage the agent to incorporate racing tactics into an integrated control policy. In addition, we construct a reward function that enables the agent to adhere to the sport's under-specified racing etiquette rules. We demonstrate the capabilities of our agent, GT Sophy, by winning two of three races against four of the world's best Gran Turismo drivers and being competitive in the overall team score. By showing that these techniques can be successfully used to train championship-level race car drivers, we open up the possibility of their use in other complex dynamical systems and real-world applications.

scholarly journals Joint Extraction of Entities and Relations Using Reinforcement Learning and Deep Learning

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Yuntian Feng ◽  
Hongjun Zhang ◽  
Wenning Hao ◽  
Gang Chen
Keyword(s):  
Deep Learning ◽  
Reinforcement Learning ◽  
Decision Process ◽  
Learning Algorithm ◽  
Relation Extraction ◽  
Control Policy ◽  
The State ◽  
Entity Extraction ◽  
Initial State ◽  
Reward Function

We use both reinforcement learning and deep learning to simultaneously extract entities and relations from unstructured texts. For reinforcement learning, we model the task as a two-step decision process. Deep learning is used to automatically capture the most important information from unstructured texts, which represent the state in the decision process. By designing the reward function per step, our proposed method can pass the information of entity extraction to relation extraction and obtain feedback in order to extract entities and relations simultaneously. Firstly, we use bidirectional LSTM to model the context information, which realizes preliminary entity extraction. On the basis of the extraction results, attention based method can represent the sentences that include target entity pair to generate the initial state in the decision process. Then we use Tree-LSTM to represent relation mentions to generate the transition state in the decision process. Finally, we employ Q-Learning algorithm to get control policy π in the two-step decision process. Experiments on ACE2005 demonstrate that our method attains better performance than the state-of-the-art method and gets a 2.4% increase in recall-score.

scholarly journals Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems

2021 ◽  
Author(s):  
Amarildo Likmeta ◽  
Alberto Maria Metelli ◽  
Giorgia Ramponi ◽  
Andrea Tirinzoni ◽  
Matteo Giuliani ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Real Life ◽  
User Preferences ◽  
Inverse Reinforcement Learning ◽  
Water Release ◽  
Reward Function ◽  
Model Free ◽  
Conflicting Objectives ◽  
Multiple Experts

AbstractIn real-world applications, inferring the intentions of expert agents (e.g., human operators) can be fundamental to understand how possibly conflicting objectives are managed, helping to interpret the demonstrated behavior. In this paper, we discuss how inverse reinforcement learning (IRL) can be employed to retrieve the reward function implicitly optimized by expert agents acting in real applications. Scaling IRL to real-world cases has proved challenging as typically only a fixed dataset of demonstrations is available and further interactions with the environment are not allowed. For this reason, we resort to a class of truly batch model-free IRL algorithms and we present three application scenarios: (1) the high-level decision-making problem in the highway driving scenario, and (2) inferring the user preferences in a social network (Twitter), and (3) the management of the water release in the Como Lake. For each of these scenarios, we provide formalization, experiments and a discussion to interpret the obtained results.

scholarly journals Sensors Integrated Control of PEMFC Gas Supply System Based on Large-Scale Deep Reinforcement Learning

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 349
Author(s):  
Jiawen Li ◽  
Tao Yu
Keyword(s):  
Reinforcement Learning ◽  
Large Scale ◽  
Integrated Control ◽  
Supply System ◽  
Proton Exchange ◽  
Coordination Problem ◽  
Hydrogen Flow ◽  
Model Free ◽  
Integrated Controller ◽  
Gas Supply

In the proton exchange membrane fuel cell (PEMFC) system, the flow of air and hydrogen is the main factor influencing the output characteristics of PEMFC, and there is a coordination problem between their flow controls. Thus, the integrated controller of the PEMFC gas supply system based on distributed deep reinforcement learning (DDRL) is proposed to solve this problem, it combines the original airflow controller and hydrogen flow controller into one. Besides, edge-cloud collaborative multiple tricks distributed deep deterministic policy gradient (ECMTD-DDPG) algorithm is presented. In this algorithm, an edge exploration policy is adopted, suggesting that the edge explores including DDPG, soft actor-critic (SAC), and conventional control algorithm are employed to realize distributed exploration in the environment, and a classified experience replay mechanism is introduced to improve exploration efficiency. Moreover, various tricks are combined with the cloud centralized training policy to address the overestimation of Q-value in DDPG. Ultimately, a model-free integrated controller of the PEMFC gas supply system with better global searching ability and training efficiency is obtained. The simulation verifies that the controller enables the flows of air and hydrogen to respond more rapidly to the changing load.

Graphical Minimax Game and Off-Policy Reinforcement Learning for Heterogeneous MASs with Spanning Tree Condition

2021 ◽  
pp. 2150011
Author(s):  
Wei Dong ◽  
Jianan Wang ◽  
Chunyan Wang ◽  
Zhenqiang Qi ◽  
Zhengtao Ding
Keyword(s):  
Reinforcement Learning ◽  
Spanning Tree ◽  
Learning Algorithm ◽  
Control Policy ◽  
Game Problem ◽  
Algebraic Riccati Equation ◽  
Multi Agent Systems ◽  
Rank Condition ◽  
Minimax Game ◽  
Tree Condition

In this paper, the optimal consensus control problem is investigated for heterogeneous linear multi-agent systems (MASs) with spanning tree condition based on game theory and reinforcement learning. First, the graphical minimax game algebraic Riccati equation (ARE) is derived by converting the consensus problem into a zero-sum game problem between each agent and its neighbors. The asymptotic stability and minimax validation of the closed-loop systems are proved theoretically. Then, a data-driven off-policy reinforcement learning algorithm is proposed to online learn the optimal control policy without the information of the system dynamics. A certain rank condition is established to guarantee the convergence of the proposed algorithm to the unique solution of the ARE. Finally, the effectiveness of the proposed method is demonstrated through a numerical simulation.

Safety-aware Adversarial Inverse Reinforcement Learning (S-AIRL) for Highway Autonomous Driving

2022 ◽  
pp. 1-14
Author(s):  
Fangjian Li ◽  
John R Wagner ◽  
Yue Wang
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Risky Behaviors ◽  
Autonomous Driving ◽  
Inverse Reinforcement Learning ◽  
Safety Issues ◽  
Reward Function ◽  
Sampling Process ◽  
Safety Awareness ◽  
Driving Scenario

Abstract Inverse reinforcement learning (IRL) has been successfully applied in many robotics and autonomous driving studies without the need for hand-tuning a reward function. However, it suffers from safety issues. Compared to the reinforcement learning (RL) algorithms, IRL is even more vulnerable to unsafe situations as it can only infer the importance of safety based on expert demonstrations. In this paper, we propose a safety-aware adversarial inverse reinforcement learning algorithm (S-AIRL). First, the control barrier function (CBF) is used to guide the training of a safety critic, which leverages the knowledge of system dynamics in the sampling process without training an additional guiding policy. The trained safety critic is then integrated into the discriminator to help discern the generated data and expert demonstrations from the standpoint of safety. Finally, to further improve the safety awareness, a regulator is introduced in the loss function of the discriminator training to prevent the recovered reward function from assigning high rewards to the risky behaviors. We tested our S-AIRL in the highway autonomous driving scenario. Comparing to the original AIRL algorithm, with the same level of imitation learning (IL) performance, the proposed S-AIRL can reduce the collision rate by 32.6%.

scholarly journals An Application of Reinforced Learning-Based Dynamic Pricing for Improvement of Ridesharing Platform Service in Seoul

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1818
Author(s):  
Jaein Song ◽  
Yun Ji Cho ◽  
Min Hee Kang ◽  
Kee Yeon Hwang
Keyword(s):  
Reinforcement Learning ◽  
Waiting Time ◽  
Dynamic Pricing ◽  
Learning Algorithm ◽  
Residential Areas ◽  
Private Companies ◽  
Reward Function ◽  
Time Period ◽  
Reinforced Learning ◽  
Centrality Analysis

As ridesharing services (including taxi) are often run by private companies, profitability is the top priority in operation. This leads to an increase in the driver’s refusal to take passengers to areas with low demand where they will have difficulties finding subsequent passengers, causing problems such as an extended waiting time when hailing a vehicle for passengers bound for these regions. The study used Seoul’s taxi data to find appropriate surge rates of ridesharing services between 10:00 p.m. and 4:00 a.m. by region using a reinforcement learning algorithm to resolve this problem during the worst time period. In reinforcement learning, the outcome of centrality analysis was applied as a weight affecting drivers’ destination choice probability. Furthermore, the reward function used in the learning was adjusted according to whether the passenger waiting time value was applied or not. The profit was used for reward value. By using a negative reward for the passenger waiting time, the study was able to identify a more appropriate surge level. Across the region, the surge averaged a value of 1.6. To be more specific, those located on the outskirts of the city and in residential areas showed a higher surge, while central areas had a lower surge. Due to this different surge, a driver’s refusal to take passengers can be lessened and the passenger waiting time can be shortened. The supply of ridesharing services in low-demand regions can be increased by as much as 7.5%, allowing regional equity problems related to ridesharing services in Seoul to be reduced to a greater extent.

scholarly journals Risk-Sensitive Reinforcement Learning Applied to Control under Constraints

2005 ◽  
Vol 24 ◽  
pp. 81-108 ◽  
Author(s):  
P. Geibel ◽  
F. Wysotzki
Keyword(s):  
Reinforcement Learning ◽  
Value Function ◽  
Learning Algorithm ◽  
Optimal Solution ◽  
Feed Tank ◽  
Model Free ◽  
Constrained Problem ◽  
Risk Sensitive ◽  
Markov Decision ◽  
The Value Function

In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with respect to a policy as the probability of entering such a state when the policy is pursued. We consider the problem of finding good policies whose risk is smaller than some user-specified threshold, and formalize it as a constrained MDP with two criteria. The first criterion corresponds to the value function originally given. We will show that the risk can be formulated as a second criterion function based on a cumulative return, whose definition is independent of the original value function. We present a model free, heuristic reinforcement learning algorithm that aims at finding good deterministic policies. It is based on weighting the original value function and the risk. The weight parameter is adapted in order to find a feasible solution for the constrained problem that has a good performance with respect to the value function. The algorithm was successfully applied to the control of a feed tank with stochastic inflows that lies upstream of a distillation column. This control task was originally formulated as an optimal control problem with chance constraints, and it was solved under certain assumptions on the model to obtain an optimal solution. The power of our learning algorithm is that it can be used even when some of these restrictive assumptions are relaxed.

scholarly journals Improvement of Vehicle Stability Using Reinforcement Learning

2018 ◽  
Author(s):  
Janaína R. Amaral ◽  
Harald Göllinger ◽  
Thiago A. Fiorentin
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Rear Wheel ◽  
Vehicle Stability ◽  
Sideslip Angle ◽  
Vehicle Handling ◽  
Race Car ◽  
Torque Vectoring ◽  
Preliminary Study ◽  
The Cost

This paper presents a preliminary study on the use of reinforcement learning to control the torque vectoring of a small rear wheel driven electric race car in order to improve vehicle handling and vehicle stability. The reinforcement learning algorithm used is Neural Fitted Q Iteration and the sampling of experiences is based on simulations of the vehicle behavior using the software CarMaker. The cost function is based on the position of the states on the phase-plane of sideslip angle and sideslip angular velocity. The resulting controller is able to improve the vehicle handling and stability with a significant reduction in vehicle sideslip angle.

scholarly journals End-to-End Deep Reinforcement Learning for Image-Based UAV Autonomous Control

2021 ◽  
Vol 11 (18) ◽  
pp. 8419
Author(s):  
Jiang Zhao ◽  
Jiaming Sun ◽  
Zhihao Cai ◽  
Longhong Wang ◽  
Yingxun Wang
Keyword(s):  
Reinforcement Learning ◽  
Network Architecture ◽  
Control Method ◽  
Control Policy ◽  
Input Image ◽  
Autonomous Control ◽  
Policy Network ◽  
Model Free ◽  
Control Command ◽  
End To End

To achieve the perception-based autonomous control of UAVs, schemes with onboard sensing and computing are popular in state-of-the-art work, which often consist of several separated modules with respective complicated algorithms. Most methods depend on handcrafted designs and prior models with little capacity for adaptation and generalization. Inspired by the research on deep reinforcement learning, this paper proposes a new end-to-end autonomous control method to simplify the separate modules in the traditional control pipeline into a single neural network. An image-based reinforcement learning framework is established, depending on the design of the network architecture and the reward function. Training is performed with model-free algorithms developed according to the specific mission, and the control policy network can map the input image directly to the continuous actuator control command. A simulation environment for the scenario of UAV landing was built. In addition, the results under different typical cases, including both the small and large initial lateral or heading angle offsets, show that the proposed end-to-end method is feasible for perception-based autonomous control.

Sign in / Sign up

Export Citation Format

Share Document