DIVA: A Self Organizing Adaptive World Model for Reinforcement Learning
نویسندگان
چکیده
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 propagate the Reinforcement Qor Vvalues much faster through the state (action) space and could be interpreted as a simple form of planning. In the following investigation we introduce a self organizing deterministic world model "DIVA" ("Discretization Improvement by VAriance reduction") with an adaptive discretization, which can speed up learning by using common methods like Suttons Dyna-Q. Proposed in this article, the "DIVA"-model is implemented in a six legged walking robot, which learns how to walk in a minimum of time and with a minimum of real world moving trials.
منابع مشابه
The Time Adaptive Self Organizing Map for Distribution Estimation
The feature map represented by the set of weight vectors of the basic SOM (Self-Organizing Map) provides a good approximation to the input space from which the sample vectors come. But the timedecreasing learning rate and neighborhood function of the basic SOM algorithm reduce its capability to adapt weights for a varied environment. In dealing with non-stationary input distributions and changi...
متن کاملAn Adaptive Learning Game for Autistic Children using Reinforcement Learning and Fuzzy Logic
This paper, presents an adapted serious game for rating social ability in children with autism spectrum disorder (ASD). The required measurements are obtained by challenges of the proposed serious game. The proposed serious game uses reinforcement learning concepts for being adaptive. It is based on fuzzy logic to evaluate the social ability level of the children with ASD. The game adapts itsel...
متن کاملCombination of Reinforcement Learning and Dynamic Self Organizing Map for Robot Arm Control
This paper shows that a system with two link arm can obtain arm reaching movement to a target object by combination of reinforcement learning and dynamic self organizing map. Proposed model in this paper present state and action space of reinforcement learning with dynamis self organizing maps. Because these spaces are continuous. proposed model uses two dynamic self-organizing maps (DSOM) to e...
متن کاملQ-learning for Robots
Robot learning is a challenging – and somewhat unique – research domain. If a robot behavior is defined as a mapping between situations that occurred in the real world and actions to be accomplished, then the supervised learning of a robot behavior requires a set of representative examples (situation, desired action). In order to be able to gather such learning base, the human operator must hav...
متن کاملSelf-Organizing Distinctive-State Abstraction For Learning Robot Navigation∗
A major challenge in reinforcement learning research is to extend methods that have worked well on discrete, shortrange, low-dimensional problems to continuous, high-diameter, high-dimensional problems, such as robot navigation using high-resolution sensors. Self-Organizing Distinctive-state Abstraction (SODA) is a new, generic method by which a robot in a continuous world can better learn to n...
متن کامل