DeepAI AI Chat
Log In Sign Up

Control Regularization for Reduced Variance Reinforcement Learning

by   Richard Cheng, et al.

Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems arising in continuous control, we propose a functional regularization approach to augmenting model-free RL. In particular, we regularize the behavior of the deep policy to be similar to a policy prior, i.e., we regularize in function space. We show that functional regularization yields a bias-variance trade-off, and propose an adaptive tuning strategy to optimize this trade-off. When the policy prior has control-theoretic stability guarantees, we further show that this regularization approximately preserves those stability guarantees throughout learning. We validate our approach empirically on a range of settings, and demonstrate significantly reduced variance, guaranteed dynamic stability, and more efficient learning than deep RL alone.


page 1

page 2

page 3

page 4


Stability-Guaranteed Reinforcement Learning for Contact-rich Manipulation

Reinforcement learning (RL) has had its fair share of success in contact...

Stability Guarantees for Continuous RL Control

Lack of stability guarantees strongly limits the use of reinforcement le...

Functional Regularization for Reinforcement Learning via Learned Fourier Features

We propose a simple architecture for deep reinforcement learning by embe...

Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning

Model-free deep reinforcement learning (RL) algorithms have been widely ...

Temporal Regularization in Markov Decision Process

Several applications of Reinforcement Learning suffer from instability d...

Soft Q-network

When DQN is announced by deepmind in 2013, the whole world is surprised ...

PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation

Proximal Policy Optimization (PPO) is a highly popular model-free reinfo...