… We present a ReinforcementLearning (RL) solution to the view planning problem (VPP), which generates a sequence of view points that are capable of sensing all accessible area of a …
… As a result, this paper uses time-series and machine learning models within a reinforcement learning approach to leverage available data and fast responsiveness to new conditions. …
O Walker, F Vanegas, F Gonzalez… - 2019 IEEE Aerospace …, 2019 - ieeexplore.ieee.org
… local planning involves optimizing a policy with respect to a future discounted reward. The primary goal of deep reinforcementlearning within our framework is therefore to learn optimal …
… of research in reinforcementlearning and decision-theoretic planning either assumes only a … familiar with single-objective reinforcementlearning and planning methods who wish to …
… This paper introduces a general framework for tactical decision making, which combines … planning and learning, in the form of Monte Carlo tree search and deep reinforcementlearning. …
… Planning The final part of the end-end pipeline is the Reinforcementlearningplanning part. This network follows the same training procedure of the DQN, with a Q-network on the top …
A Pan, W Xu, L Wang, H Ren - Knowledge-Based Systems, 2020 - Elsevier
… The pseudocode of reinforcementlearning with additional planning is detailed in Algorithm 3. According to the two different approaches introduced in Section 3.1, the two RLAP …
… learning algorithms. To do so, we define sufficient criteria for a sample-based planner to be used in such a learning … We also introduce our own sample-based planner, which combines …
… In this section, we show that DDPG and SAC can learn optimal trajectory planning for dynamic obstacles collision avoidance. For the evaluation, we compare two different DRL …