Acceleration method for deep reinforcement learning of simulation robot

Abstract

The invention belongs to the field of robots, discloses an acceleration method for deep reinforcement learning of a simulation robot, and aims to accelerate the learning process so as to reduce the time expenditure of robot deep reinforcement learning research, debugging and deployment. According to the technical scheme, one node is selected as a learning node, and other nodes are selected as environment nodes; each environment node processes interaction details with one robot simulator instance and provides a unified environment interaction message interface; and the learning node performs environment interaction with each environment node through a message interface in a frame simulation form, and learning data is collected from multiple environments, so that reinforced learning is accelerated. According to the method, while the environment nodes are abstracted to adapt to various robot simulators, learning algorithm development and simulation interaction details are decoupled, message communication allows the environment nodes and simulator instances to be deployed in a distributed computing environment, and the method has the advantages of being easy to deploy and extensible.

Description

technical field [0001] The invention belongs to the field of robots, and relates to an acceleration method for deep reinforcement learning of robots in a simulation environment, and can be applied to robot control tasks such as obstacle avoidance, navigation, formation, and multi-robot collaboration of intelligent robots. Background technique [0002] Reinforcement learning is one of the important technologies used in the field of robotics. Through reinforcement learning, robots can learn a set of action strategies to complete tasks independently through continuous attempts. This self-learning ability plays an important role in complex scenarios where it is difficult to manually design action strategies. significance. [0003] Reinforcement learning is used to solve sequential decision-making problems. The learner (that is, the agent) tries to make an action according to the action strategy combined with the current environment state (the initial strategy is usually a random...

AI Technical Summary

Problems solved by technology

For simulation-based learning, on the one hand, the simulation environment is required to be as realistic as possible, so that the learning results can be more easily transferred to reality, but on the other hand, the more realistic the simulation environment, the greater the computational cost. The cost of training time, the evolution of the simulation environment has become a bottleneck that limits the speed of deep reinforcement learning for robots

Images