Author name cluster

Fei Feng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

ICML Conference 2021 Conference Paper

Provably Correct Optimization and Exploration with Non-linear Policies

Fei Feng
Wotao Yin
Alekh Agarwal
Lin F. Yang

Policy optimization methods remain a powerful workhorse in empirical Reinforcement Learning (RL), with a focus on neural policies that can easily reason over complex and continuous state and/or action spaces. Theoretical understanding of strategic exploration in policy-based methods with non-linear function approximation, however, is largely missing. In this paper, we address this question by designing ENIAC, an actor-critic method that allows non-linear function approximation in the critic. We show that under certain assumptions, e. g. , a bounded eluder dimension $d$ for the critic class, the learner finds to a near-optimal policy in $\widetilde{O}(\mathrm{poly}(d))$ exploration rounds. The method is robust to model misspecification and strictly extends existing works on linear function approximation. We also develop some computational optimizations of our approach with slightly worse statistical guarantees, and an empirical adaptation building on existing deep RL tools. We empirically evaluate this adaptation, and show that it outperforms prior heuristics inspired by linear methods, establishing the value in correctly reasoning about the agent’s uncertainty under non-linear function approximation.

Details

NeurIPS Conference 2020 Conference Paper

Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning

Fei Feng
Ruosong Wang
Wotao Yin
Simon S. Du
Lin Yang

Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems [tang2017exploration, bellemare2016unifying], we investigate when this paradigm is provably efficient. We study episodic Markov decision processes with rich observations generated from a small number of latent states. We present a general algorithmic framework that is built upon two components: an unsupervised learning algorithm and a no-regret tabular RL algorithm. Theoretically, we prove that as long as the unsupervised learning algorithm enjoys a polynomial sample complexity guarantee, we can find a near-optimal policy with sample complexity polynomial in the number of latent states, which is significantly smaller than the number of observations. Empirically, we instantiate our framework on a class of hard exploration problems to demonstrate the practicality of our theory.

PDF Details

ICML Conference 2019 Conference Paper

Acceleration of SVRG and Katyusha X by Inexact Preconditioning

Yanli Liu 0003
Fei Feng
Wotao Yin

Empirical risk minimization is an important class of optimization problems with many popular machine learning applications, and stochastic variance reduction methods are popular choices for solving them. Among these methods, SVRG and Katyusha X (a Nesterov accelerated SVRG) achieve fast convergence without substantial memory requirement. In this paper, we propose to accelerate these two algorithms by inexact preconditioning, the proposed methods employ fixed preconditioners, although the subproblem in each epoch becomes harder, it suffices to apply fixed number of simple subroutines to solve it inexactly, without losing the overall convergence. As a result, this inexact preconditioning strategy gives provably better iteration complexity and gradient complexity over SVRG and Katyusha X. We also allow each function in the finite sum to be nonconvex while the sum is strongly convex. In our numerical experiments, we observe an on average $8\times$ speedup on the number of iterations and $7\times$ speedup on runtime.

Details