Bo Liu

Zifan Xu, Bo Liu, Xuesu Xiao et al.

Deep reinforcement learning (RL) has brought many successes for autonomous robot navigation. However, there still exists important limitations that prevent real-world use of RL-based navigation systems. For example, most learning approaches lack safety guarantees; and learned navigation systems may not generalize well to unseen environments. Despite a variety of recent learning techniques to tackle these challenges in general, a lack of an open-source benchmark and reproducible learning methods specifically for autonomous navigation makes it difficult for roboticists to choose what learning methods to use for their mobile robots and for learning researchers to identify current shortcomings of general learning methods for autonomous navigation. In this paper, we identify four major desiderata of applying deep RL approaches for autonomous navigation: (D1) reasoning under uncertainty, (D2) safety, (D3) learning from limited trial-and-error data, and (D4) generalization to diverse and novel environments. Then, we explore four major classes of learning techniques with the purpose of achieving one or more of the four desiderata: memory-based neural network architectures (D1), safe RL (D2), model-based RL (D2, D3), and domain randomization (D4). By deploying these learning techniques in a new open-source large-scale navigation benchmark and real-world environments, we perform a comprehensive study aimed at establishing to what extent can these techniques achieve these desiderata for RL-based navigation systems.

Bo Liu, Yihao Feng, Qiang Liu et al. · apple-ml

Goal-conditioned reinforcement learning (GCRL) has a wide range of potential real-world applications, including manipulation and navigation problems in robotics. Especially in such robotics tasks, sample efficiency is of the utmost importance for GCRL since, by default, the agent is only rewarded when it reaches its goal. While several methods have been proposed to improve the sample efficiency of GCRL, one relatively under-studied approach is the design of neural architectures to support sample efficiency. In this work, we introduce a novel neural architecture for GCRL that achieves significantly better sample efficiency than the commonly-used monolithic network architecture. The key insight is that the optimal action-value function Q^*(s, a, g) must satisfy the triangle inequality in a specific sense. Furthermore, we introduce the metric residual network (MRN) that deliberately decomposes the action-value function Q(s,a,g) into the negated summation of a metric plus a residual asymmetric component. MRN provably approximates any optimal action-value function Q^*(s,a,g), thus making it a fitting neural architecture for GCRL. We conduct comprehensive experiments across 12 standard benchmark environments in GCRL. The empirical results demonstrate that MRN uniformly outperforms other state-of-the-art GCRL neural architectures in terms of sample efficiency.

Lizhang Chen, Bo Liu, Kaizhao Liang et al.

Lion (Evolved Sign Momentum), a new optimizer discovered through program search, has shown promising results in training large AI models. It performs comparably or favorably to AdamW but with greater memory efficiency. As we can expect from the results of a random search program, Lion incorporates elements from several existing algorithms, including signed momentum, decoupled weight decay, Polak, and Nesterov momentum, but does not fit into any existing category of theoretically grounded optimizers. Thus, even though Lion appears to perform well as a general-purpose optimizer for a wide range of tasks, its theoretical basis remains uncertain. This lack of theoretical clarity limits opportunities to further enhance and expand Lion's efficacy. This work aims to demystify Lion. Based on both continuous-time and discrete-time analysis, we demonstrate that Lion is a theoretically novel and principled approach for minimizing a general loss function $f(x)$ while enforcing a bound constraint $\|x\|_\infty \leq 1/λ$. Lion achieves this through the incorporation of decoupled weight decay, where $λ$ represents the weight decay coefficient. Our analysis is made possible by the development of a new Lyapunov function for the Lion updates. It applies to a broader family of Lion-$κ$ algorithms, where the $\text{sign}(\cdot)$ operator in Lion is replaced by the subgradient of a convex function $κ$, leading to the solution of a general composite optimization problem of $\min_x f(x) + κ^*(x)$. Our findings provide valuable insights into the dynamics of Lion and pave the way for further improvements and extensions of Lion-related algorithms.

Liangliang Xu, Daoming Lyu, Yangchen Pan et al.

It remains challenging to deploy existing risk-averse approaches to real-world applications. The reasons are multi-fold, including the lack of global optimality guarantee and the necessity of learning from long-term consecutive trajectories. Long-term consecutive trajectories are prone to involving visiting hazardous states, which is a major concern in the risk-averse setting. This paper proposes Short-Term VOlatility-controlled Policy Search (STOPS), a novel algorithm that solves risk-averse problems by learning from short-term trajectories instead of long-term trajectories. Short-term trajectories are more flexible to generate, and can avoid the danger of hazardous state visitations. By using an actor-critic scheme with an overparameterized two-layer neural network, our algorithm finds a globally optimal policy at a sublinear rate with proximal policy optimization and natural policy gradient, with effectiveness comparable to the state-of-the-art convergence rate of risk-neutral policy-search methods. The algorithm is evaluated on challenging Mujoco robot simulation tasks under the mean-variance evaluation metric. Both theoretical analysis and experimental results demonstrate a state-of-the-art level of STOPS' performance among existing risk-averse policy search methods.

Qishen Ha, Bo Liu, Fuxu Liu et al.

We present our third place solution to the Google Landmark Recognition 2020 competition. It is an ensemble of global features only Sub-center ArcFace models. We introduce dynamic margins for ArcFace loss, a family of tune-able margin functions of class size, designed to deal with the extreme imbalance in GLDv2 dataset. Progressive finetuning and careful postprocessing are also key to the solution. Our two submissions scored 0.6344 and 0.6289 on private leaderboard, both ranking third place out of 736 teams.

Daoming Lyu, Qi Qi, Mohammad Ghavamzadeh et al.

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues with convergence. A few variance-reduced on-policy policy gradient algorithms have been recently proposed that use methods from stochastic optimization to reduce the variance of the gradient estimate in the REINFORCE algorithm. However, these algorithms are not designed for the off-policy setting and are memory-inefficient, since they need to collect and store a large ``reference'' batch of samples from time to time. To achieve variance-reduced off-policy-stable policy optimization, we propose an algorithm family that is memory-efficient, stochastically variance-reduced, and capable of learning from off-policy samples. Empirical studies validate the effectiveness of the proposed approaches.

Bo Liu, Ji Liu, Mohammad Ghavamzadeh et al.

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techniques to prove asymptotic convergence, and to the best of our knowledge, no finite-sample analysis has been done. Moreover, there has been not much work on finite-sample analysis for convergent off-policy reinforcement learning algorithms. In this paper, we formulate GTD methods as stochastic gradient algorithms w.r.t.~a primal-dual saddle-point objective function, and then conduct a saddle-point error analysis to obtain finite-sample bounds on their performance. Two revised algorithms are also proposed, namely projected GTD2 and GTD2-MP, which offer improved convergence guarantees and acceleration, respectively. The results of our theoretical analysis show that the GTD family of algorithms are indeed comparable to the existing LSTD methods in off-policy learning scenarios.

Shangtong Zhang, Bo Liu, Shimon Whiteson

We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable. MVPI enjoys great flexibility in that any policy evaluation method and risk-neutral control method can be dropped in for risk-averse control off the shelf, in both on- and off-policy settings. This flexibility reduces the gap between risk-neutral control and risk-averse control and is achieved by working on a novel augmented MDP directly. We propose risk-averse TD3 as an example instantiating MVPI, which outperforms vanilla TD3 and many previous risk-averse control methods in challenging Mujoco robot simulation tasks under a risk-aware performance metric. This risk-averse TD3 is the first to introduce deterministic policies and off-policy learning into risk-averse reinforcement learning, both of which are key to the performance boost we show in Mujoco domains.

Daoming Lyu, Fangkai Yang, Bo Liu et al.

Conventional reinforcement learning (RL) allows an agent to learn policies via environmental rewards only, with a long and slow learning curve, especially at the beginning stage. On the contrary, human learning is usually much faster because prior and general knowledge and multiple information resources are utilized. In this paper, we propose a \textbf{P}lanner-\textbf{A}ctor-\textbf{C}ritic architecture for hu\textbf{MAN}-centered planning and learning (\textbf{PACMAN}), where an agent uses prior, high-level, deterministic symbolic knowledge to plan for goal-directed actions. PACMAN integrates Actor-Critic algorithm of RL to fine-tune its behavior towards both environmental rewards and human feedback. To the best our knowledge, This is the first unified framework where knowledge-based planning, RL, and human teaching jointly contribute to the policy learning of an agent. Our experiments demonstrate that PACMAN leads to a significant jump-start at the early stage of learning, converges rapidly and with small variance, and is robust to inconsistent, infrequent, and misleading feedback.