MLDRL: A multi-layer distributed reinforcement learning framework with multiple trainers
نویسندگان
چکیده
منابع مشابه
A Multi-Objective Deep Reinforcement Learning Framework
This paper presents a new multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We propose linear and non-linear methods to develop the MODRL framework that includes both single-policy and multi-policy strategies. The experimental results on a deep sea treasure environment indicate that the proposed approach is able to converge to the optimal Pareto solutions. ...
متن کاملA Distributed Reinforcement Learning Scheme for Network Markov Games as a Framework for Multi-agent Reinforcement Learning. 8.2 Discussion
Consider an electronic market where agents can interact and trade. The agents involved in the market are completely autonomous and act on behalf of their masters. In such a multi-agent system, where other agents may be potential partners, or competing opponents, an agent should have the ability to identify the other agents' intentions and goals and to be able to predict the others' future behav...
متن کاملHierarchical Robot Controll with Multi Layer Perceptrons and Reinforcement Learning
Abstract. Several hierarchical algorithms have been proposed for reinforcement learning [Barto, 2003] (RL). On this work, we propose another one, that makes possible to map the set of actions of the robot on a set of uncoupled actions, that some independent RL controllers will care about, and use neural networks to generate the physical ones. While applying it into a simulated mechanical arm, w...
متن کاملRay RLlib: A Framework for Distributed Reinforcement Learning
Reinforcement learning (RL) algorithms involve the deep nesting of distinct components, where each component typically exhibits opportunities for distributed computation. Current RL libraries offer parallelism at the level of the entire program, coupling all the components together and making existing implementations difficult to extend, combine, and reuse. We argue for building composable RL c...
متن کاملA Framework for Aggregation of Multiple Reinforcement Learning Algorithms
Aggregation of multiple Reinforcement Learning (RL) algorithms is a new and effective technique to improve the quality of Sequential Decision Making (SDM). SDM is very common and important in various realistic applications, especially in automatic control problems. The quality of a SDM depends on (discounted) long-term rewards rather than the instant rewards. Due to delayed feedback, SDM tasks ...
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: Journal of Physics: Conference Series
سال: 2021
ISSN: 1742-6588,1742-6596
DOI: 10.1088/1742-6596/1883/1/012160