Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience
نویسندگان
چکیده
منابع مشابه
Actor-Critic Policy Learning in Cooperative Planning
In this paper, we introduce a method for learning and adapting cooperative control strategies in real-time stochastic domains. Our framework is an instance of the intelligent cooperative control architecture (iCCA). The agent starts by following the “safe” plan calculated by the planning module and incrementally adapting its policy to maximize the cumulative rewards. Actor-critic and consensusb...
متن کاملEfficient Actor-Critic Algorithm with Hierarchical Model Learning and Planning
To improve the convergence rate and the sample efficiency, two efficient learning methods AC-HMLP and RAC-HMLP (AC-HMLP with ℓ2-regularization) are proposed by combining actor-critic algorithm with hierarchical model learning and planning. The hierarchical models consisting of the local and the global models, which are learned at the same time during learning of the value function and the polic...
متن کاملACtuAL: Actor-Critic Under Adversarial Learning
Generative Adversarial Networks (GANs) are a powerful framework for deep generative modeling. Posed as a two-player minimax problem, GANs are typically trained end-to-end on real-valued data and can be used to train a generator of high-dimensional and realistic images. However, a major limitation of GANs is that training relies on passing gradients from the discriminator through the generator v...
متن کاملAdaptive Motion Planning for Complex Planning Problems
Motion planning has been used to solve problems of high complexity in both robotic and biological domains. In robotics, the topology of the planning environment often drives the problem’s complexity. Environments can consist of many different regions each of which may be well suited to a specific planning approach. In biological domains, problem complexity is primarily driven by the size of the...
متن کاملAdversarial Hierarchical-Task Network Planning for Real-Time Adversarial Games
Real-time strategy (RTS) games are hard from an AI point of view because they have enormous state spaces, combinatorial branching factors, allow simultaneous and durative actions, and players have very little time to choose actions. For these reasons, standard game tree search methods such as alphabeta search or Monte Carlo Tree Search (MCTS) are not sufficient by themselves to handle these gam...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2019
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v33i01.33018017