Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs

Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether hybrid RL can improve upon the existing lower bounds established in purely offline and purely online RL without relying on the single-policy concentrability assumption. While Li et al. (2023) provided an affirmative answer to this question in the tabular PAC RL case, the question remains unsettled for both the regret-minimizing RL case and the non-tabular case. In this work, building upon recent advancements in offline RL and reward-agnostic exploration, we develop computationally efficient algorithms for both PAC and regret-minimizing RL with linear function approximation, without single-policy concentrability. We demonstrate that these algorithms achieve sharper error or regret bounds that are no worse than, and can improve on, the optimal sample complexity in offline RL (the first algorithm, for PAC RL) and online RL (the second algorithm, for regret-minimizing RL) in linear Markov decision processes (MDPs), regardless of the quality of the behavior policy. To our knowledge, this work establishes the tightest theoretical guarantees currently available for hybrid RL in linear MDPs.

Accelerated Inference for Partially Observed Markov Processes using Automatic Differentiation

Automatic differentiation (AD) has driven recent advances in machine learning, including deep neural networks and Hamiltonian Markov Chain Monte Carlo methods. Partially observed nonlinear stochastic dynamical systems have proved resistant to AD techniques because widely used particle filter algorithms yield an estimated likelihood function that is discontinuous as a function of the model parameters. We show how to embed two existing AD particle filter methods in a theoretical framework that provides an extension to a new class of algorithms. This new class permits a bias/variance tradeoff and hence a mean squared error substantially lower than the existing algorithms. We develop likelihood maximization algorithms suited to the Monte Carlo properties of the AD gradient estimate. Our algorithms require only a differentiable simulator for the latent dynamic system; by contrast, most previous approaches to AD likelihood maximization for particle filters require access to the system's transition probabilities. Numerical results indicate that a hybrid algorithm that uses AD to refine a coarse solution from an iterated filtering algorithm show substantial improvement on current state-of-the-art methods for a challenging scientific benchmark problem.

Leveraging Offline Data in Linear Latent Bandits

Sequential decision-making domains such as recommender systems, healthcare and education often have unobserved heterogeneity in the population that can be modeled using latent bandits $-$ a framework where an unobserved latent state determines the model for a trajectory. While the latent bandit framework is compelling, the extent of its generality is unclear. We first address this by establishing a de Finetti theorem for decision processes, and show that $\textit{every}$ exchangeable and coherent stateless decision process is a latent bandit. The latent bandit framework lends itself particularly well to online learning with offline datasets, a problem of growing interest in sequential decision-making. One can leverage offline latent bandit data to learn a complex model for each latent state, so that an agent can simply learn the latent state online to act optimally. We focus on a linear model for a latent bandit with $d_A$-dimensional actions, where the latent states lie in an unknown $d_K$-dimensional subspace for $d_K \ll d_A$. We present SOLD, a novel principled method to learn this subspace from short offline trajectories with guarantees. We then provide two methods to leverage this subspace online: LOCAL-UCB and ProBALL-UCB. We demonstrate that LOCAL-UCB enjoys $\tilde O(\min(d_A\sqrt{T}, d_K\sqrt{T}(1+\sqrt{d_AT/d_KN})))$ regret guarantees, where the effective dimension is lower when the size $N$ of the offline dataset is larger. ProBALL-UCB enjoys a slightly weaker guarantee, but is more practical and computationally efficient. Finally, we establish the efficacy of our methods using experiments on both synthetic data and real-life movie recommendation data from MovieLens.

Distributed Least Squares in Small Space via Sketching and Bias Reduction

Matrix sketching is a powerful tool for reducing the size of large data matrices. Yet there are fundamental limitations to this size reduction when we want to recover an accurate estimator for a task such as least square regression. We show that these limitations can be circumvented in the distributed setting by designing sketching methods that minimize the bias of the estimator, rather than its error. In particular, we give a sparse sketching method running in optimal space and current matrix multiplication time, which recovers a nearly-unbiased least squares estimator using two passes over the data. This leads to new communication-efficient distributed averaging algorithms for least squares and related tasks, which directly improve on several prior approaches. Our key novelty is a new bias analysis for sketched least squares, giving a sharp characterization of its dependence on the sketch sparsity. The techniques include new higher-moment restricted Bai-Silverstein inequalities, which are of independent interest to the non-asymptotic analysis of deterministic equivalents for random matrices that arise from sketching.

A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage

Hybrid Reinforcement Learning (RL), leveraging both online and offline data, has garnered recent interest, yet research on its provable benefits remains sparse. Additionally, many existing hybrid RL algorithms (Song et al., 2023; Nakamoto et al., 2023; Amortila et al., 2024) impose coverage assumptions on the offline dataset, but we show that this is unnecessary. A well-designed online algorithm should "fill in the gaps" in the offline dataset, exploring states and actions that the behavior policy did not explore. Unlike previous approaches that focus on estimating the offline data distribution to guide online exploration (Li et al., 2023b), we show that a natural extension to standard optimistic online algorithms -- warm-starting them by including the offline dataset in the experience replay buffer -- achieves similar provable gains from hybrid data even when the offline dataset does not have single-policy concentrability. We accomplish this by partitioning the state-action space into two, bounding the regret on each partition through an offline and an online complexity measure, and showing that the regret of this hybrid RL algorithm can be characterized by the best partition -- despite the algorithm not knowing the partition itself. As an example, we propose DISC-GOLF, a modification of an existing optimistic online algorithm with general function approximation called GOLF used in Jin et al. (2021); Xie et al. (2022a), and show that it demonstrates provable gains over both online-only and offline-only reinforcement learning, with competitive bounds when specialized to the tabular, linear and block MDP cases. Numerical simulations further validate our theory that hybrid data facilitates more efficient exploration, supporting the potential of hybrid RL in various scenarios.

Offline Policy Evaluation and Optimization under Confounding

With a few exceptions, work in offline reinforcement learning (RL) has so far assumed that there is no confounding. In a classical regression setting, confounders introduce omitted variable bias and inhibit the identification of causal effects. In offline RL, they prevent the identification of a policy's value, and therefore make it impossible to perform policy improvement. Using conventional methods in offline RL in the presence of confounding can therefore not only lead to poor decisions and poor policies, but can also have disastrous effects in applications such as healthcare and education. We provide approaches for both off-policy evaluation (OPE) and local policy optimization in the settings of i.i.d. and global confounders. Theoretical and empirical results confirm the validity and viability of these methods.

Learning Mixtures of Markov Chains and MDPs

We present an algorithm for use in learning mixtures of both Markov chains (MCs) and Markov decision processes (offline latent MDPs) from trajectories, with roots dating back to the work of Vempala and Wang. This amounts to handling Markov chains with optional control input. The method is modular in nature and amounts to (1) a subspace estimation step, (2) spectral clustering of trajectories, and (3) a few iterations of the EM algorithm. We provide end-to-end performance guarantees where we only explicitly require the number of trajectories to be linear in states and the trajectory length to be linear in mixing time. Experimental results suggest it outperforms both EM (95.4% on average) and a previous method by Gupta et al. (54.1%), obtaining 100% permuted accuracy on an 8x8 gridworld.

Objective Micro-Facial Movement Detection Using FACS-Based Regions and Baseline Evaluation

Micro-facial expressions are regarded as an important human behavioural event that can highlight emotional deception. Spotting these movements is difficult for humans and machines, however research into using computer vision to detect subtle facial expressions is growing in popularity. This paper proposes an individualised baseline micro-movement detection method using 3D Histogram of Oriented Gradients (3D HOG) temporal difference method. We define a face template consisting of 26 regions based on the Facial Action Coding System (FACS). We extract the temporal features of each region using 3D HOG. Then, we use Chi-square distance to find subtle facial motion in the local regions. Finally, an automatic peak detector is used to detect micro-movements above the newly proposed adaptive baseline threshold. The performance is validated on two FACS coded datasets: SAMM and CASME II. This objective method focuses on the movement of the 26 face regions. When comparing with the ground truth, the best result was an AUC of 0.7512 and 0.7261 on SAMM and CASME II, respectively. The results show that 3D HOG outperformed for micro-movement detection, compared to state-of-the-art feature representations: Local Binary Patterns in Three Orthogonal Planes and Histograms of Oriented Optical Flow.