Reinforcement Learning with Policy Constraints
نویسندگان
چکیده
This paper addresses the problem of knowledge transfer in lifelong reinforcement learning. It proposes an algorithm which learns policy constraints, i.e., rules that characterize action selection in entire families of reinforcement learning tasks. Once learned, policy constraints are used to bias learning in future, similar reinforcement learning tasks. The appropriateness of the algorithm is demonstrated in two domains: A grid world domain and a (more challenging) light control problem for commercial office space. Submitted to ICML-98
منابع مشابه
Nonconvex Policy Search Using Variational Inequalities
Policy search is a class of reinforcement learning algorithms for finding optimal policies in control problems with limited feedback. These methods have been shown to be successful in high-dimensional problems such as robotics control. Though successful, current methods can lead to unsafe policy parameters that potentially could damage hardware units. Motivated by such constraints, we propose p...
متن کاملReinforcement Learning in Robotics: Applications and Real-World Challenges
In robotics, the ultimate goal of reinforcement learning is to endow robots with the ability to learn, improve, adapt and reproduce tasks with dynamically changing constraints based on exploration and autonomous learning. We give a summary of the state-of-the-art of reinforcement learning in the context of robotics, in terms of both algorithms and policy representations. Numerous challenges fac...
متن کاملRTP-Q: A Reinforcement Learning System with Time Constraints Exploration Planning for Accelerating the Learning Rate
Reinforcement learning is an efficient method for solving Markov Decision Processes that an agent improves its performance by using scalar reward values with higher capability of reactive and adaptive behaviors. Q-learning is a representative reinforcement learning method which is guaranteed to obtain an optimal policy but needs numerous trials to achieve it. k-Certainty Exploration Learning Sy...
متن کاملCall Admission Control in Wireless Ds-cdma Systems Using Reinforcement Learning
THAI) สาขาวิชาวิศวกรรมโทรคมนาคม ลายมือช่ือนักศึกษา ปการศึกษา 2549 ลายมือช่ืออาจารยที่ปรึกษา PITIPONG CHANLOHA : CALL ADMISSION CONTROL IN WIRELESS DS-CDMA SYSTEMS USING REINFORCEMENT LEARNING. THESIS ADVISOR : ASST. PROF. WIPAWEE HATTAGAM, Ph.D. 95 PP. ABSTRACT (ENGLISH) DIRECT-SEQUENTIAL CODE DIVISION MULTIPLE ACCESS (DS-CDMA)/ CALL ADMISSION CONTROL/ REINFORCEMENT LEARNING/ ACTOR-CRITIC REINFO...
متن کاملConstrained Policy Optimization
For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact with or around humans should satisfy safety constraints. Recent advances in policy search algorithms (Mnih et al., 2016; Schulman et al., 2015; Lillicrap et al...
متن کامل