Online state space generation by a growing self-organizing map and differential learning for reinforcement learning
نویسندگان
چکیده
منابع مشابه
Self-organizing Developmental Reinforcement Learning
This paper presents a developmental reinforcement learning framework aimed at exploring rich, complex and large sensorimotor spaces. The core of this architecture is made of a function approximator based on a Dynamic Self-Organizing Map (DSOM). The life-long online learning property of the DSOM allows us to take a developmental approach to learning a robotic task: the perception and motor skill...
متن کاملSelf-organizing Neural Architecture for Reinforcement Learning
Self-organizing neural networks are typically associated with unsupervised learning. This paper presents a self-organizing neural architecture, known as TD-FALCON, that learns cognitive codes across multi-modal pattern spaces, involving states, actions, and rewards, and is capable of adapting and functioning in a dynamic environment with external evaluative feedback signals. We present a case s...
متن کاملA Constant Learning Rate Self-Organizing Map (CLRSOM) Learning Algorithm
In a conventional SOM, it is of utmost importance that a certain and consistently decreasing learning rate function be chosen. Decrease the learning rate too fast, the map will not get converged and the performance of the SOM may take a steep fall, and if too slow, the procedure would take a large amount of time to get carried out. For overcoming this problem, we have hereafter proposed a const...
متن کاملState Space Reduction For Hierarchical Reinforcement Learning
This paper provides new techniques for abstracting the state space of a Markov Decision Process (MDP). These techniques extend one of the recent minimization models, known as -reduction, to construct a partition space that has a smaller number of states than the original MDP. As a result, learning policies on the partition space should be faster than on the original state space. The technique p...
متن کاملDIVA: A Self Organizing Adaptive World Model for Reinforcement Learning
Reinforcement learning algorithms without an internal world model often su er from overly long time to converge. Mostly the agent has to be successful a several hundred times before it could learn how to behave in even simple environments. In this case, a world model could be useful to reduce the number of real world trials by performing the action virtually in the world model. This may help to...
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: Applied Soft Computing
سال: 2020
ISSN: 1568-4946
DOI: 10.1016/j.asoc.2020.106723