Authors:
Lei Li
;
Lei Wang
;
Yuanzhi Li
and
Jie Sheng
Affiliation:
Department of Automation, University of Science and Technology of China, Hefei 230027, Anhui, China
Keyword(s):
Reinforcement Learning, Behavior Tree, Intelligent Agents, Option Framework, Unity 3D.
Abstract:
Intelligent agent design has increasingly enjoyed the great advancements in real-world applications but most agents are also required to possess the capacities of learning and adapt to complicated environments. In this work, we investigate a general and extendable model of mixed behavior tree (MDRL-BT) upon the option framework where the hierarchical architecture simultaneously involves different deep reinforcement learning nodes and normal BT nodes. The emphasis of this improved model lies in the combination of neural network learning and restrictive behavior framework without conflicts. Moreover, the collaborative nature of two aspects can bring the benefits of expected intelligence, scalable behaviors and flexible strategies for agents. Afterwards, we enable the execution of the model and search for the general construction pattern by focusing on popular deep RL algorithms, PPO and SAC. Experimental performances in both Unity 2D and 3D environments demonstrate the feasibility and
practicality of MDRL-BT by comparison with the-state-of-art models. Furthermore, we embed the curiosity mechanism into the MDRL-BT to facilitate the extensions.
(More)