Fei Feng

Fei Feng, Wotao Yin, Alekh Agarwal et al.

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 a near-optimal policy in $O(\poly(d))$ 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 via correctly reasoning about the agent's uncertainty under non-linear function approximation.

Fei Feng, Ruosong Wang, Wotao Yin et al.

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.

Fei Feng, Wotao Yin, Lin F. Yang

One of the key approaches to save samples in reinforcement learning (RL) is to use knowledge from an approximate model such as its simulator. However, how much does an approximate model help to learn a near-optimal policy of the true unknown model? Despite numerous empirical studies of transfer reinforcement learning, an answer to this question is still elusive. In this paper, we study the sample complexity of RL while an approximate model of the environment is provided. For an unknown Markov decision process (MDP), we show that the approximate model can effectively reduce the complexity by eliminating sub-optimal actions from the policy searching space. In particular, we provide an algorithm that uses $\widetilde{O}(N/(1-γ)^3/\varepsilon^2)$ samples in a generative model to learn an $\varepsilon$-optimal policy, where $γ$ is the discount factor and $N$ is the number of near-optimal actions in the approximate model. This can be much smaller than the learning-from-scratch complexity $\widetildeΘ(SA/(1-γ)^3/\varepsilon^2)$, where $S$ and $A$ are the sizes of state and action spaces respectively. We also provide a lower bound showing that the above upper bound is nearly-tight if the value gap between near-optimal actions and sub-optimal actions in the approximate model is sufficiently large. Our results provide a very precise characterization of how an approximate model helps reinforcement learning when no additional assumption on the model is posed.

Yibo Zeng, Fei Feng, Wotao Yin

In this paper, we propose AsyncQVI, an asynchronous-parallel Q-value iteration for discounted Markov decision processes whose transition and reward can only be sampled through a generative model. Given such a problem with $|\mathcal{S}|$ states, $|\mathcal{A}|$ actions, and a discounted factor $γ\in(0,1)$, AsyncQVI uses memory of size $\mathcal{O}(|\mathcal{S}|)$ and returns an $\varepsilon$-optimal policy with probability at least $1-δ$ using $$\tilde{\mathcal{O}}\big(\frac{|\mathcal{S}||\mathcal{A}|}{(1-γ)^5\varepsilon^2}\log(\frac{1}δ)\big)$$ samples. AsyncQVI is also the first asynchronous-parallel algorithm for discounted Markov decision processes that has a sample complexity, which nearly matches the theoretical lower bound. The relatively low memory footprint and parallel ability make AsyncQVI suitable for large-scale applications. In numerical tests, we compare AsyncQVI with four sample-based value iteration methods. The results show that our algorithm is highly efficient and achieves linear parallel speedup.