# Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning

arXiv: https://arxiv.org/abs/2002.02697 · HTML: https://mlsanity.com/paper/2002.02697/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2020.

## Built on by (most cited first, 13 of 13)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Self-Imitation Learning by Planning](https://mlsanity.com/paper/2103.13834/) (2021)
- [Boost Your Human Image Generation Model via Direct Preference Optimization](https://mlsanity.com/paper/2405.20216/) (2024)
- [Open-World Drone Active Tracking with Goal-Centered Rewards](https://mlsanity.com/paper/2412.00744/) (2024)
- [Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control](https://mlsanity.com/paper/2111.10005/) (2021)
- [Aligned Multi Objective Optimization](https://mlsanity.com/paper/2502.14096/) (2025)
- [Increasing Interaction Fidelity: Training Routines for Biomechanical Models in HCI](https://mlsanity.com/paper/2508.16581/) (2025)
- [Accelerating Robot Learning of Contact-Rich Manipulations: A Curriculum Learning Study](https://mlsanity.com/paper/2204.12844/) (2022)
- [Human-Inspired Framework to Accelerate Reinforcement Learning](https://mlsanity.com/paper/2303.08115/) (2023)
- [Monolithic vs. hybrid controller for multi-objective Sim-to-Real learning](https://mlsanity.com/paper/2108.07514/) (2021)
- [Dual-Arm Adversarial Robot Learning](https://mlsanity.com/paper/2110.08066/) (2021)
- [Meta Arcade: A Configurable Environment Suite for Meta-Learning](https://mlsanity.com/paper/2112.00583/) (2021)
- [Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark](https://mlsanity.com/paper/2607.15935/) (2026)

## Abstract (arXiv)

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.