REVIEW 2 cited by
Regularization Matters in Policy Optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Deep Reinforcement Learning (Deep RL) has been receiving increasingly more attention thanks to its encouraging performance on a variety of control tasks. Yet, conventional regularization techniques in training neural networks (e.g., $L_2$ regularization, dropout) have been largely ignored in RL methods, possibly because agents are typically trained and evaluated in the same environment, and because the deep RL community focuses more on high-level algorithm designs. In this work, we present the first comprehensive study of regularization techniques with multiple policy optimization algorithms on continuous control tasks. Interestingly, we find conventional regularization techniques on the policy networks can often bring large improvement, especially on harder tasks. Our findings are shown to be robust against training hyperparameter variations. We also compare these techniques with the more widely used entropy regularization. In addition, we study regularizing different components and find that only regularizing the policy network is typically the best. We further analyze why regularization may help generalization in RL from four perspectives - sample complexity, reward distribution, weight norm, and noise robustness. We hope our study provides guidance for future practices in regularizing policy optimization algorithms. Our code is available at https://github.com/xuanlinli17/iclr2021_rlreg .
Forward citations
Cited by 2 Pith papers
-
Bridging Adaptivity and Safety: Learning Agile Collision-Free Locomotion Across Varied Physics
A legged-robot controller that estimates payload and friction online and uses those estimates to switch between agile and recovery policies achieves lower collision rates and higher speeds than non-adaptive baselines.
-
The impact of intrinsic rewards on exploration in Reinforcement Learning
An empirical MiniGrid study shows state-counting is best for low-dimensional observations, maximum entropy is more robust with images, and DIAYN skill learning does not aid exploration.
Discussion (0). Continue with ORCID to comment.