How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?
arXiv:1903.11774
Abstract
Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising successes in applying RL algorithms directly on real systems, their performance on more complex systems remains bottle-necked by the relative data inefficiency of RL algorithms. Domain randomization is a promising direction of research that has demonstrated impressive results using RL algorithms to control real robots. At a high level, domain randomization works by training a policy on a distribution of environmental conditions in simulation. If the environments are diverse enough, then the policy trained on this distribution will plausibly generalize to the real world. A human-specified design choice in domain randomization is the form and parameters of the distribution of simulated environments. It is unclear how to the best pick the form and parameters of this distribution and prior work uses hand-tuned distributions. This extended abstract demonstrates that the choice of the distribution plays a major role in the performance of the trained policies in the real world and that the parameter of this distribution can be optimized to maximize the performance of the trained policies in the real world
arXiv comment2-page extended abstract
References in corpus (9)
- Auto-Encoding Variational Bayes
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Addressing Function Approximation Error in Actor-Critic Methods
- Learning agile and dynamic motor skills for legged robots
- CMA-ES for Hyperparameter Optimization of Deep Neural Networks
- Simple random search provides a competitive approach to reinforcement learning
- SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning
- Benchmarking Reinforcement Learning Algorithms on Real-World Robots
- Policies Modulating Trajectory Generators