Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning

Abstract

Reinforcement learning has shown great promise in the training of robot behavior due to the sequential decision making characteristics. However, the required enormous amount of interactive and informative training data provides the major stumbling block for progress. In this study, we focus on accelerating reinforcement learning (RL) training and improving the performance of multi-goal reaching tasks. Specifically, we propose a precision-based continuous curriculum learning (PCCL) method in which the requirements are gradually adjusted during the training process, instead of fixing the parameter in a static schedule. To this end, we explore various continuous curriculum strategies for controlling a training process. This approach is tested using a Universal Robot 5e in both simulation and real-world multi-goal reach experiments. Experimental results support the hypothesis that a static training schedule is suboptimal, and using an appropriate decay function for curriculum learning provides superior results in a faster way.

References in corpus (12)

• Continuous control with deep reinforcement learning
• Trust Region Policy Optimization
• Deep Learning using Rectified Linear Units (ReLU)
• Prioritized Experience Replay
• End-to-End Training of Deep Visuomotor Policies
• OpenAI Gym
• Hindsight Experience Replay
• Data-Efficient Hierarchical Reinforcement Learning
• Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
• Deep Reinforcement Learning for Robotic Manipulation-The state of the art
• Accuracy-based Curriculum Learning in Deep Reinforcement Learning
• Learning Directed Locomotion in Modular Robots with Evolvable Morphologies

Cited by in corpus (7)

• Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control
• Increasing Interaction Fidelity: Training Routines for Biomechanical Models in HCI
• HiER: Highlight Experience Replay for Boosting Off-Policy Reinforcement Learning Agents
• Self-Imitation Learning by Planning
• The State of Lifelong Learning in Service Robots: Current Bottlenecks in Object Perception and Manipulation
• Meta Arcade: A Configurable Environment Suite for Meta-Learning
• Dual-Arm Adversarial Robot Learning