Utilizing negative policy information to accelerate reinforcement learning
نویسنده
چکیده
ACKNOWLEDGEMENTS One consequence of my long tenure at Georgia Tech has been the opportunity to get to know a large number of exceptional people. I'm thankful for tremendous support from some particularly exceptional people: advisor Charles Isbell, a gentleman and a scholar, who gave me the opportunity to think outside the box; and my adoptive advisor Andrea Thomaz, who helped me see it's also quite a good idea to stop and focus on the box long enough to get a bow onto it.
منابع مشابه
Utilizing Generalized Learning Automata for Finding Optimal Policies in MMDPs
Multi agent Markov decision processes (MMDPs), as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi agent system and are used as a suitable framework for Multi agent Reinforcement Learning. In this paper, a generalized learning automata based algorithm for finding optimal policies in MMDP is proposed. In the proposed algorithm, MMDP ...
متن کاملAccelerate Learning Processes by Avoiding Inappropriate Rules in Transfer Learning for Actor - Critic
hh tt tt Abstruct—This paper aims to accelerate processes of actor-critic method, which is one of major reinforcement learning algorithms, by a transfer learning. In general, reinforcement learning is used to solve optimization problems. Learning agents acquire a policy to accomplish the target task autonomously. To solve the problems, agents require long learning processes for trial and error....
متن کاملSpeeding-up reinforcement learning through abstraction and transfer learning
We are interested in the following general question: is it possible to abstract knowledge that is generated while learning the solution of a problem, so that this abstraction can accelerate the learning process? Moreover, is it possible to transfer and reuse the acquired abstract knowledge to accelerate the learning process for future similar tasks? We propose a framework for conducting simulta...
متن کاملTime Variable Reinforcement Learning and Reinforcement Function Design
We introduce the mathematical model for time variable reinforcement learning. The policy, the rewards or reinforcement function and the transition probabilities may depend on the progress of the time t. We prove that under certain conditions slightly changed methods of classical dynamic programming assure finding the optimal policy. For that we deduct the Bellman equation for the time variable ...
متن کاملPolicy Shaping: Integrating Human Feedback with Reinforcement Learning
A long term goal of Interactive Reinforcement Learning is to incorporate nonexpert human feedback to solve complex tasks. Some state-of-the-art methods have approached this problem by mapping human information to rewards and values and iterating over them to compute better control policies. In this paper we argue for an alternate, more effective characterization of human feedback: Policy Shapin...
متن کامل