2024 · 10 citations · 23 references
EngineeringComputer ScienceRobotics EngineeringMachine LearningRobot LearningRoboticsExploration-exploitation TradeoffPolicy IterationPolicy LearningReinforcement LearningExploration In Reinforcement LearningQuadruped LocomotionReinforcement Learning For Robotics
In Reinforcement Learning, the trade-off between exploration and exploitation poses a complex challenge for achieving efficient learning from limited samples. While recent works have been effective in leveraging past experiences for policy updates, they often overlook the potential of reusing past experiences for data collection. Independent of the underlying RL algorithm, we introduce the concept of a Contrastive Initial State Buffer, which strategically selects states from past experiences and uses them to initialize the agent in the environment in order to guide it toward more informative states. We validate our approach on two complex robotic tasks without relying on any prior information about the environment: (i) locomotion of a quadruped robot traversing challenging terrains and (ii) a quadcopter drone racing through a track. The experimental results show that our initial state buffer achieves higher task performance than the nominal baseline while also speeding up training convergence.
23
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Deep Reinforcement Learning: A Brief Survey
Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage et al. · IEEE Signal Processing Magazine · 2017 · 4.3K citations
Tom Schaul, John Quan, Ioannis Antonoglou et al. · arXiv (Cornell University) · 2015 · 2K citations · Full text