Evolution of Meta-parameters in Reinforcement Learning
نویسندگان
چکیده
A crucial issue in reinforcement learning applications is how to set meta-parameters, such as the learning rate and ”temperature” for exploration, to match the demands of the task and the environment. In this thesis, a method to adjust meta-parameters of reinforcement learning by using a real-number genetic algorithm is proposed. Simulations of foraging tasks show that appropriate settings of meta-parameters, which are strongly dependent on each other, can be found by evolution. Furthermore, hardware experiments using Cyber Rodent robots verify that the meta-parameters evolved in simulation are helpful for learning in real hardware. Evolution av meta-parametrar i reinforcement learning
منابع مشابه
Embodied Evolution of Learning Ability
Embodied evolution is a methodology for evolutionary robotics that mimics the distributed, asynchronous, and autonomous properties of biological evolution. The evaluation, selection, and reproduction are carried out by cooperation and competition of the robots, without any need for human intervention. An embodied evolution framework is therefore well suited to study the adaptive learning mechan...
متن کاملEvolution of meta-parameters in reinforcement learning algorithm
In most Reinforcment Learning approches, the metaparameters such as learning rate and ”temperatur” for exploration are adjusted manually. In order to build fully autonomous learning agents, it is important to develop methods for adjusting these parameters to match the demands of the task and the environment. In this paper, we propose a new method to determine the values of meta parameters in re...
متن کاملNeural Networks letter Meta-learning in Reinforcement Learning
Meta-parameters in reinforcement learning should be tuned to the environmental dynamics and the animal performance. Here, we propose a biologically plausible meta-reinforcement learning algorithm for tuning these meta-parameters in a dynamic, adaptive manner. We tested our algorithm in both a simulation of a Markov decision task and in a non-linear control task. Our results show that the algori...
متن کاملOnline Meta-learning by Parallel Algorithm Competition
The efficiency of reinforcement learning algorithms depends critically on a few metaparameters that modulates the learning updates and the trade-off between exploration and exploitation. The adaptation of the meta-parameters is an open question in reinforcement learning, which arguably has become more of an issue recently with the success of deep reinforcement learning in high-dimensional state...
متن کاملA Monte Carlo-Based Search Strategy for Dimensionality Reduction in Performance Tuning Parameters
Redundant and irrelevant features in high dimensional data increase the complexity in underlying mathematical models. It is necessary to conduct pre-processing steps that search for the most relevant features in order to reduce the dimensionality of the data. This study made use of a meta-heuristic search approach which uses lightweight random simulations to balance between the exploitation of ...
متن کامل