Compatible Reward Inverse Reinforcement Learning
نویسندگان
چکیده
PROBLEM • Inverse Reinforcement Learning (IRL) problem: recover a reward function explaining a set of expert’s demonstrations. • Advantages of IRL over Behavioral Cloning (BC): – Transferability of the reward. • Issues with some IRL methods: – How to build the features for the reward function? – How to select a reward function among all the optimal ones? – What if no access to the environment? CONTRIBUTIONS 1. We propose the Compatible Reward Inverse Reinforcement Learning (CR-IRL): • CR-IRL is model-free since it requires solely a set of expert’s demonstrations; • CR-IRL performs both feature extraction and reward selection. 2. We provide empirical results to show that the rewards recovered by CRIRL allow learning the optimal policy faster than the original reward function.
منابع مشابه
Nonlinear Inverse Reinforcement Learning with Gaussian Processes
We present a probabilistic algorithm for nonlinear inverse reinforcement learning. The goal of inverse reinforcement learning is to learn the reward function in a Markov decision process from expert demonstrations. While most prior inverse reinforcement learning algorithms represent the reward as a linear combination of a set of features, we use Gaussian processes to learn the reward as a nonli...
متن کاملInverse Optimal Control
In Reinforcement Learning, an agent learns a policy that maximizes a given reward function. However, providing a reward function for a given learning task is often non trivial. Inverse Reinforcement Learning, which is sometimes also called Inverse Optimal Control, addresses this problem by learning the reward function from expert demonstrations. The aim of this paper is to give a brief introduc...
متن کاملThe Use of Apprenticeship Learning Via Inverse Reinforcement Learning for Generating Melodies
The research presented in this paper uses apprenticeship learning via inverse reinforcement learning to ascertain a reward function in a musical context. The learning agent then used this reward function to generate new melodies using reinforcement learning. Reinforcement learning is a type of unsupervised machine learning where rewards are used to guide an agent’s learning. These rewards are u...
متن کاملOptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectori...
متن کاملInverse Reinforcement Learning based on Critical State
Inverse reinforcement learning is tried to search a reward function based on Markov Decision Process. In the IRL topics, experts produce some good traces to make agents learn and adjust the reward function. But the function is difficult to set in some complicate problems. In this paper, Inverse Reinforcement Learning based on Critical State (IRLCS) is proposed to search a succinct and meaningfu...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017