Reinforcement learning with replacing eligibility traces
Machine Learning - Special issue on reinforcement learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Reinforcement Learning in the Multi-Robot Domain
Autonomous Robots
Reinforcement Learning and Shaping: Encouraging Intended Behaviors
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Learning to Drive a Bicycle Using Reinforcement Learning and Shaping
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Efficient Reinforcement Learning Through Evolving Neural Network Topologies
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines
Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Autonomous shaping: knowledge transfer in reinforcement learning
ICML '06 Proceedings of the 23rd international conference on Machine learning
Evolutionary Function Approximation for Reinforcement Learning
The Journal of Machine Learning Research
Automatic shaping and decomposition of reward functions
Proceedings of the 24th international conference on Machine learning
Potential-based shaping and Q-value initialization are equivalent
Journal of Artificial Intelligence Research
Evolutionary Development of Hierarchical Learning Structures
IEEE Transactions on Evolutionary Computation
Multi-task evolutionary shaping without pre-specified representations
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Darwinian embodied evolution of the learning ability for survival
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
TAROS'11 Proceedings of the 12th Annual conference on Towards autonomous robotic systems
Multi-Task reinforcement learning: shaping and feature selection
EWRL'11 Proceedings of the 9th European conference on Recent Advances in Reinforcement Learning
Learning potential functions and their representations for multi-task reinforcement learning
Autonomous Agents and Multi-Agent Systems
Hi-index | 0.00 |
In this article, we explore an evolutionary approach to theoptimization of potential-based shaping rewards and meta-parametersin reinforcement learning. Shaping rewards is a frequently usedapproach to increase the learning performance of reinforcementlearning, with regards to both initial performance and convergencespeed. Shaping rewards provide additional knowledge to the agent inthe form of richer reward signals, which guide learning tohigh-rewarding states. Reinforcement learning depends critically ona few meta-parameters that modulate the learning updates or theexploration of the environment, such as the learning rate α,the discount factor of future rewards γ, and the temperatureτ that controls the trade-off between exploration andexploitation in softmax action selection. We validate the proposedapproach in simulation using the mountain-car task. We alsotransfer shaping rewards and meta-parameters, evolutionarilyobtained in simulation, to hardware, using a robotic foragingtask.