Reinforcement learning in the environment where optimal action value function is partly discontinuous

2016 ◽  
Author(s):  
Shingo Shibusawa ◽  
Takeshi Shibuya
Keyword(s):  
Reinforcement Learning ◽  
Value Function ◽  
Optimal Action ◽  
Action Value

scholarly journals Reinforcement Learning for Optimizing Driving Policies on Cruising Taxis Services

2020 ◽  
Vol 12 (21) ◽  
pp. 8883
Author(s):  
Kun Jin ◽  
Wei Wang ◽  
Xuedong Hua ◽  
Wei Zhou
Keyword(s):  
Reinforcement Learning ◽  
Value Function ◽  
State Action ◽  
Future Reward ◽  
Long Run ◽  
Markov Decision ◽  
Action Value ◽  
Data Expansion ◽  
Taking Action ◽  
The Value Function

As the key element of urban transportation, taxis services significantly provide convenience and comfort for residents’ travel. However, the reality has not shown much efficiency. Previous researchers mainly aimed to optimize policies by order dispatch on ride-hailing services, which cannot be applied in cruising taxis services. This paper developed the reinforcement learning (RL) framework to optimize driving policies on cruising taxis services. Firstly, we formulated the drivers’ behaviours as the Markov decision process (MDP) progress, considering the influences after taking action in the long run. The RL framework using dynamic programming and data expansion was employed to calculate the state-action value function. Following the value function, drivers can determine the best choice and then quantify the expected future reward at a particular state. By utilizing historic orders data in Chengdu, we analysed the function value’s spatial distribution and demonstrated how the model could optimize the driving policies. Finally, the realistic simulation of the on-demand platform was built. Compared with other benchmark methods, the results verified that the new model performs better in increasing total revenue, answer rate and decreasing waiting time, with the relative percentages of 4.8%, 6.2% and −27.27% at most.

scholarly journals Determinantal Reinforcement Learning

2019 ◽  
Vol 33 ◽  
pp. 4659-4666
Author(s):  
Takayuki Osogami ◽  
Rudy Raymond
Keyword(s):  
Reinforcement Learning ◽  
Value Function ◽  
Positive Semidefinite ◽  
Positive Semidefinite Matrix ◽  
The Matrix ◽  
Multi Agent ◽  
Action Value ◽  
The Individual ◽  
Partially Observable ◽  
Semidefinite Matrix

We study reinforcement learning for controlling multiple agents in a collaborative manner. In some of those tasks, it is insufficient for the individual agents to take relevant actions, but those actions should also have diversity. We propose the approach of using the determinant of a positive semidefinite matrix to approximate the action-value function in reinforcement learning, where we learn the matrix in a way that it represents the relevance and diversity of the actions. Experimental results show that the proposed approach allows the agents to learn a nearly optimal policy approximately ten times faster than baseline approaches in benchmark tasks of multi-agent reinforcement learning. The proposed approach is also shown to achieve the performance that cannot be achieved with conventional approaches in partially observable environment with exponentially large action space.

scholarly journals A solution for the Elevators Group Dispatch by Multiagent Reinforcement Learning

2019 ◽  
Author(s):  
Jordão Memória ◽  
José Maia
Keyword(s):  
Reinforcement Learning ◽  
Function Approximation ◽  
Value Function ◽  
The State ◽  
Evaluation Function ◽  
State Action ◽  
Traffic Pattern ◽  
Multiagent Reinforcement Learning ◽  
Multi Agent ◽  
Action Value

In this work, a modeling and algorithm based on multiagent reinforcement learning is developed for the problem of elevator group dispatch. The main advantage is that, along with the function approximation, this multi-agent solution leads to reduction of the state space, allowing complex states to be addressed with a synthesizing evaluation function. Each elevator is considered an agent that have to decide about two actions: answer or ignore the new call. With some iterations, the agents learn the weights of an evaluation function which approximate the state-action value function. The performance of solution (average waiting time - AWT), shown varying the traffic pattern, flow of people, number of elevators and number of floors, is comparable to other current proposals reported in the literature.

scholarly journals Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 5948-5955
Author(s):  
Tian Tan ◽  
Zhihan Xiong ◽  
Vikranth R. Dwaracherla
Keyword(s):  
Reinforcement Learning ◽  
Network Architecture ◽  
Value Function ◽  
Point Of View ◽  
Value Functions ◽  
Computationally Efficient ◽  
Computational Point ◽  
Action Value ◽  
Efficient Exploration ◽  
Computational Resources

It is well known that quantifying uncertainty in the action-value estimates is crucial for efficient exploration in reinforcement learning. Ensemble sampling offers a relatively computationally tractable way of doing this using randomized value functions. However, it still requires a huge amount of computational resources for complex problems. In this paper, we present an alternative, computationally efficient way to induce exploration using index sampling. We use an indexed value function to represent uncertainty in our action-value estimates. We first present an algorithm to learn parameterized indexed value function through a distributional version of temporal difference in a tabular setting and prove its regret bound. Then, in a computational point of view, we propose a dual-network architecture, Parameterized Indexed Networks (PINs), comprising one mean network and one uncertainty network to learn the indexed value function. Finally, we show the efficacy of PINs through computational experiments.

scholarly journals Multi-Agent/Robot Deep Reinforcement Learning with Macro-Actions (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13965-13966
Author(s):  
Yuchen Xiao ◽  
Joshua Hoffman ◽  
Tian Xia ◽  
Christopher Amato
Keyword(s):  
Reinforcement Learning ◽  
Value Function ◽  
Action Observation ◽  
Action Selection ◽  
New Approaches ◽  
Multi Agent ◽  
Action Value

We consider the challenges of learning multi-agent/robot macro-action-based deep Q-nets including how to properly update each macro-action value and accurately maintain macro-action-observation trajectories. We address these challenges by first proposing two fundamental frameworks for learning macro-action-value function and joint macro-action-value function. Furthermore, we present two new approaches of learning decentralized macro-action-based policies, which involve a new double Q-update rule that facilitates the learning of decentralized Q-nets by using a centralized Q-net for action selection. Our approaches are evaluated both in simulation and on real robots.

scholarly journals Energy Management of Hybrid UAV Based on Reinforcement Learning

Electronics ◽  
2021 ◽  
Vol 10 (16) ◽  
pp. 1929
Author(s):  
Huan Shen ◽  
Yao Zhang ◽  
Jianguo Mao ◽  
Zhiwei Yan ◽  
Linwei Wu
Keyword(s):  
Reinforcement Learning ◽  
State Space ◽  
Energy Management ◽  
Internal Combustion Engines ◽  
Value Function ◽  
Learning Algorithm ◽  
The State ◽  
Combustion Engines ◽  
State Action ◽  
Action Value

In order to solve the flight time problem of Unmanned Aerial Vehicles (UAV), this paper proposes a set of energy management strategies based on reinforcement learning for hybrid agricultural UAV. The battery is used to optimize the working point of internal combustion engines to the greatest extent while solving the high power demand issues of UAV and the response problem of internal combustion engines. Firstly, the decision-making oriented hybrid model and UAV dynamic model are established. Owing to the characteristics of the energy management strategy (EMS) based on reinforcement learning (RL), which is an intelligent optimization algorithm that has emerged in recent years, the complex theoretical formula derivation is avoided in the modeling process. In terms of the EMS, a double Q learning algorithm with strong convergence is adopted. The algorithm separates the state action value function database used in derivation decisions and the state action value function-updated database brought by the decision, so as to avoid delay and shock within the convergence process caused by maximum deviation. After the improvement, the off-line training is carried out with a large number of flight data generated in the past. The simulation results demonstrate that the improved algorithm can show better performance with less learning cost than before by virtue of the search function strategy proposed in this paper. In the state space, time-based and residual fuel-based selection are carried out successively, and the convergence rate and application effect are compared and analyzed. The results show that the learning algorithm has stronger robustness and convergence speed due to the appropriate selection of state space under different types of operating cycles. After 120,000 cycles of training, the fuel economy of the improved algorithm in this paper can reach more than 90% of that of the optimal solution, and can perform stably in actual flight.

scholarly journals Improved Q-Learning Algorithm Based on Approximate State Matching in Agricultural Plant Protection Environment

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 737
Author(s):  
Fengjie Sun ◽  
Xianchang Wang ◽  
Rui Zhang
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Optimal Policy ◽  
Feasible Solution ◽  
Learning Algorithm ◽  
Plant Protection ◽  
Agricultural Plant ◽  
Q Learning ◽  
Aerial Vehicle ◽  
Optimal Action

An Unmanned Aerial Vehicle (UAV) can greatly reduce manpower in the agricultural plant protection such as watering, sowing, and pesticide spraying. It is essential to develop a Decision-making Support System (DSS) for UAVs to help them choose the correct action in states according to the policy. In an unknown environment, the method of formulating rules for UAVs to help them choose actions is not applicable, and it is a feasible solution to obtain the optimal policy through reinforcement learning. However, experiments show that the existing reinforcement learning algorithms cannot get the optimal policy for a UAV in the agricultural plant protection environment. In this work we propose an improved Q-learning algorithm based on similar state matching, and we prove theoretically that there has a greater probability for UAV choosing the optimal action according to the policy learned by the algorithm we proposed than the classic Q-learning algorithm in the agricultural plant protection environment. This proposed algorithm is implemented and tested on datasets that are evenly distributed based on real UAV parameters and real farm information. The performance evaluation of the algorithm is discussed in detail. Experimental results show that the algorithm we proposed can efficiently learn the optimal policy for UAVs in the agricultural plant protection environment.

Sign in / Sign up

Export Citation Format

Share Document