# Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control

arXiv: https://arxiv.org/abs/1802.04765 · HTML: https://mlsanity.com/paper/1802.04765/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2018.

## Built on by (most cited first, 14 of 14)

- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation](https://mlsanity.com/paper/2210.07686/) (2022)
- [Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation](https://mlsanity.com/paper/2104.01655/) (2021)
- [GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model](https://mlsanity.com/paper/2104.09771/) (2021)
- [ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments](https://mlsanity.com/paper/2407.18550/) (2024)
- [CoMPS: Continual Meta Policy Search](https://mlsanity.com/paper/2112.04467/) (2021)
- [Learning multiple gaits of quadruped robot using hierarchical reinforcement learning](https://mlsanity.com/paper/2112.04741/) (2021)
- [Selective Cross-Task Distillation](https://mlsanity.com/paper/2204.11526/) (2022)
- [IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse](https://mlsanity.com/paper/2308.07351/) (2023)
- [SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learning](https://mlsanity.com/paper/2502.12674/) (2025)
- [GPO: Growing Policy Optimization for Legged Robot Locomotion and Whole-Body Control](https://mlsanity.com/paper/2601.20668/) (2026)
- [Self-Imitation Learning of Locomotion Movements through Termination Curriculum](https://mlsanity.com/paper/1907.11842/) (2019)
- [On Neural Consolidation for Transfer in Reinforcement Learning](https://mlsanity.com/paper/2210.02240/) (2022)
- [PTRL: Prior Transfer Deep Reinforcement Learning for Legged Robots Locomotion](https://mlsanity.com/paper/2504.05629/) (2025)

## Abstract (arXiv)

Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing good strategies for integrating or merging policies for multiple skills, where each individual skill is a specialist in a specific skill and its associated state distribution. We extend policy distillation methods to the continuous action setting and leverage this technique to combine expert policies, as evaluated in the domain of simulated bipedal locomotion across different classes of terrain. We also introduce an input injection method for augmenting an existing policy network to exploit new input features. Lastly, our method uses transfer learning to assist in the efficient acquisition of new skills. The combination of these methods allows a policy to be incrementally augmented with new skills. We compare our progressive learning and integration via distillation (PLAID) method against three alternative baselines.