Reinforcement learning and its application to control
Reinforcement learning and its application to control
Numerical methods for stochastic control problems in continuous time
Numerical methods for stochastic control problems in continuous time
TD-Gammon, a self-teaching backgammon program, achieves master-level play
Neural Computation
The first law of robotics (a call to arms)
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Temporal difference learning and TD-Gammon
Communications of the ACM
Robust nonlinear control design: state-space and Lyapunov techniques
Robust nonlinear control design: state-space and Lyapunov techniques
Mathematical control theory: deterministic finite dimensional systems (2nd ed.)
Mathematical control theory: deterministic finite dimensional systems (2nd ed.)
Elevator Group Control Using Multiple Reinforcement Learning Agents
Machine Learning
Risk sensitive reinforcement learning
Proceedings of the 1998 conference on Advances in neural information processing systems II
Reinforcement Learning
Introduction to Robotics: Mechanics and Control
Introduction to Robotics: Mechanics and Control
Nonlinear and Adaptive Control Design
Nonlinear and Adaptive Control Design
Nonlinear and Optimal Control Systems
Nonlinear and Optimal Control Systems
Neuro-Dynamic Programming
Variable Resolution Discretization in Optimal Control
Machine Learning
Hidden Strengths and Limitations: An Empirical Investigation of Reinforcement Learning
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Lyapunov-Constrained Action Sets for Reinforcement Learning
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
A synthesis of reinforcement learning and robust control theory
A synthesis of reinforcement learning and robust control theory
Approximate solutions to markov decision processes
Approximate solutions to markov decision processes
Lyapunov methods for safe intelligent agent design
Lyapunov methods for safe intelligent agent design
Journal of Artificial Intelligence Research
Heuristic search in infinite state spaces guided by Lyapunov analysis
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
Survey A survey of computational complexity results in systems and control
Automatica (Journal of IFAC)
Recent Advances in Hierarchical Reinforcement Learning
Discrete Event Dynamic Systems
Recent Advances in Hierarchical Reinforcement Learning
Discrete Event Dynamic Systems
Safe learning with real-time constraints: a case study
IEA/AIE'10 Proceedings of the 23rd international conference on Industrial engineering and other applications of applied intelligent systems - Volume Part I
Safe robot learning by energy limitation
ICIRA'12 Proceedings of the 5th international conference on Intelligent Robotics and Applications - Volume Part III
Smart exploration in reinforcement learning using absolute temporal difference errors
Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems
Study of similar motion imitation of stepping upstairs for humanoid robot
International Journal of Computing Science and Mathematics
Reinforcement learning in robotics: A survey
International Journal of Robotics Research
Hi-index | 0.00 |
Lyapunov design methods are used widely in control engineering to design controllers that achieve qualitative objectives, such as stabilizing a system or maintaining a system's state in a desired operating range. We propose a method for constructing safe, reliable reinforcement learning agents based on Lyapunov design principles. In our approach, an agent learns to control a system by switching among a number of given, base-level controllers. These controllers are designed using Lyapunov domain knowledge so that any switching policy is safe and enjoys basic performance guarantees. Our approach thus ensures qualitatively satisfactory agent behavior for virtually any reinforcement learning algorithm and at all times, including while the agent is learning and taking exploratory actions. We demonstrate the process of designing safe agents for four different control problems. In simulation experiments, we find that our theoretically motivated designs also enjoy a number of practical benefits, including reasonable performance initially and throughout learning, and accelerated learning.