Boosting Offline Reinforcement Learning via Data Rebalancing

Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly constrain the learned policy to be close to the behavior policy. The constraint applies not only to well-performing actions but also to inferior ones, which limits the performance upper bound of the learned policy. Instead of aligning the densities of two distributions, aligning the supports gives a relaxed constraint while still being able to avoid out-of-distribution actions. Therefore, we propose a simple yet effective method to boost offline RL algorithms based on the observation that resampling a dataset keeps the distribution support unchanged. More specifically, we construct a better behavior policy by resampling each transition in an old dataset according to its episodic return. We dub our method ReD (Return-based Data Rebalance), which can be implemented with less than 10 lines of code change and adds negligible running time. Extensive experiments demonstrate that ReD is effective at boosting offline RL performance and orthogonal to decoupling strategies in long-tailed classification. New state-of-the-arts are achieved on the D4RL benchmark.

Mutual Information Regularized Offline Reinforcement Learning

Offline reinforcement learning (RL) aims at learning an effective policy from offline datasets without active interactions with the environment. The major challenge of offline RL is the distribution shift that appears when out-of-distribution actions are queried, which makes the policy improvement direction biased by extrapolation errors. Most existing methods address this problem by penalizing the policy for deviating from the behavior policy during policy improvement or making conservative updates for value functions during policy evaluation. In this work, we propose a novel MISA framework to approach offline RL from the perspective of Mutual Information between States and Actions in the dataset by directly constraining the policy improvement direction. Intuitively, mutual information measures the mutual dependence of actions and states, which reflects how a behavior agent reacts to certain environment states during data collection. To effectively utilize this information to facilitate policy learning, MISA constructs lower bounds of mutual information parameterized by the policy and Q-values. We show that optimizing this lower bound is equivalent to maximizing the likelihood of a one-step improved policy on the offline dataset. In this way, we constrain the policy improvement direction to lie in the data manifold. The resulting algorithm simultaneously augments the policy evaluation and improvement by adding a mutual information regularization. MISA is a general offline RL framework that unifies conservative Q-learning (CQL) and behavior regularization methods (e.g., TD3+BC) as special cases. Our experiments show that MISA performs significantly better than existing methods and achieves new state-of-the-art on various tasks of the D4RL benchmark.

Understanding and Optimizing Deep Learning Cold-Start Latency on Edge Devices

DNNs are ubiquitous on edge devices nowadays. With its increasing importance and use cases, it's not likely to pack all DNNs into device memory and expect that each inference has been warmed up. Therefore, cold inference, the process to read, initialize, and execute a DNN model, is becoming commonplace and its performance is urgently demanded to be optimized. To this end, we present NNV12, the first on-device inference engine that optimizes for cold inference NNV12 is built atop 3 novel optimization knobs: selecting a proper kernel (implementation) for each DNN operator, bypassing the weights transformation process by caching the post-transformed weights on disk, and pipelined execution of many kernels on asymmetric processors. To tackle with the huge search space, NNV12 employs a heuristic-based scheme to obtain a near-optimal kernel scheduling plan. We fully implement a prototype of NNV12 and evaluate its performance across extensive experiments. It shows that NNV12 achieves up to 15.2x and 401.5x compared to the state-of-the-art DNN engines on edge CPUs and GPUs, respectively.

Imitation Learning via Differentiable Physics

Existing imitation learning (IL) methods such as inverse reinforcement learning (IRL) usually have a double-loop training process, alternating between learning a reward function and a policy and tend to suffer long training time and high variance. In this work, we identify the benefits of differentiable physics simulators and propose a new IL method, i.e., Imitation Learning via Differentiable Physics (ILD), which gets rid of the double-loop design and achieves significant improvements in final performance, convergence speed, and stability. The proposed ILD incorporates the differentiable physics simulator as a physics prior into its computational graph for policy learning. It unrolls the dynamics by sampling actions from a parameterized policy, simply minimizing the distance between the expert trajectory and the agent trajectory, and back-propagating the gradient into the policy via temporal physics operators. With the physics prior, ILD policies can not only be transferable to unseen environment specifications but also yield higher final performance on a variety of tasks. In addition, ILD naturally forms a single-loop structure, which significantly improves the stability and training speed. To simplify the complex optimization landscape induced by temporal physics operations, ILD dynamically selects the learning objectives for each state during optimization. In our experiments, we show that ILD outperforms state-of-the-art methods in a variety of continuous control tasks with Brax, requiring only one expert demonstration. In addition, ILD can be applied to challenging deformable object manipulation tasks and can be generalized to unseen configurations.

Label Adversarial Learning for Skeleton-level to Pixel-level Adjustable Vessel Segmentation

You can have your cake and eat it too. Microvessel segmentation in optical coherence tomography angiography (OCTA) images remains challenging. Skeleton-level segmentation shows clear topology but without diameter information, while pixel-level segmentation shows a clear caliber but low topology. To close this gap, we propose a novel label adversarial learning (LAL) for skeleton-level to pixel-level adjustable vessel segmentation. LAL mainly consists of two designs: a label adversarial loss and an embeddable adjustment layer. The label adversarial loss establishes an adversarial relationship between the two label supervisions, while the adjustment layer adjusts the network parameters to match the different adversarial weights. Such a design can efficiently capture the variation between the two supervisions, making the segmentation continuous and tunable. This continuous process allows us to recommend high-quality vessel segmentation with clear caliber and topology. Experimental results show that our results outperform manual annotations of current public datasets and conventional filtering effects. Furthermore, such a continuous process can also be used to generate an uncertainty map representing weak vessel boundaries and noise.

Hierarchical Reinforcement Learning under Mixed Observability

The framework of mixed observable Markov decision processes (MOMDP) models many robotic domains in which some state variables are fully observable while others are not. In this work, we identify a significant subclass of MOMDPs defined by how actions influence the fully observable components of the state and how those, in turn, influence the partially observable components and the rewards. This unique property allows for a two-level hierarchical approach we call HIerarchical Reinforcement Learning under Mixed Observability (HILMO), which restricts partial observability to the top level while the bottom level remains fully observable, enabling higher learning efficiency. The top level produces desired goals to be reached by the bottom level until the task is solved. We further develop theoretical guarantees to show that our approach can achieve optimal and quasi-optimal behavior under mild assumptions. Empirical results on long-horizon continuous control tasks demonstrate the efficacy and efficiency of our approach in terms of improved success rate, sample efficiency, and wall-clock training time. We also deploy policies learned in simulation on a real robot.

A Comprehensive Benchmark of Deep Learning Libraries on Mobile Devices

Deploying deep learning (DL) on mobile devices has been a notable trend in recent years. To support fast inference of on-device DL, DL libraries play a critical role as algorithms and hardware do. Unfortunately, no prior work ever dives deep into the ecosystem of modern DL libs and provides quantitative results on their performance. In this paper, we first build a comprehensive benchmark that includes 6 representative DL libs and 15 diversified DL models. We then perform extensive experiments on 10 mobile devices, which help reveal a complete landscape of the current mobile DL libs ecosystem. For example, we find that the best-performing DL lib is severely fragmented across different models and hardware, and the gap between those DL libs can be rather huge. In fact, the impacts of DL libs can overwhelm the optimizations from algorithms or hardware, e.g., model quantization and GPU/DSP-based heterogeneous computing. Finally, atop the observations, we summarize practical implications to different roles in the DL lib ecosystem.

On Exploring Pose Estimation as an Auxiliary Learning Task for Visible-Infrared Person Re-identification

Visible-infrared person re-identification (VI-ReID) has been challenging due to the existence of large discrepancies between visible and infrared modalities. Most pioneering approaches reduce intra-class variations and inter-modality discrepancies by learning modality-shared and ID-related features. However, an explicit modality-shared cue, i.e., body keypoints, has not been fully exploited in VI-ReID. Additionally, existing feature learning paradigms imposed constraints on either global features or partitioned feature stripes, which neglect the prediction consistency of global and part features. To address the above problems, we exploit Pose Estimation as an auxiliary learning task to assist the VI-ReID task in an end-to-end framework. By jointly training these two tasks in a mutually beneficial manner, our model learns higher quality modality-shared and ID-related features. On top of it, the learnings of global features and local features are seamlessly synchronized by Hierarchical Feature Constraint (HFC), where the former supervises the latter using the knowledge distillation strategy. Experimental results on two benchmark VI-ReID datasets show that the proposed method consistently improves state-of-the-art methods by significant margins. Specifically, our method achieves nearly 20$\%$ mAP improvements against the state-of-the-art method on the RegDB dataset. Our intriguing findings highlight the usage of auxiliary task learning in VI-ReID.

State-based Episodic Memory for Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) algorithms have made promising progress in recent years by leveraging the centralized training and decentralized execution (CTDE) paradigm. However, existing MARL algorithms still suffer from the sample inefficiency problem. In this paper, we propose a simple yet effective approach, called state-based episodic memory (SEM), to improve sample efficiency in MARL. SEM adopts episodic memory (EM) to supervise the centralized training procedure of CTDE in MARL. To the best of our knowledge, SEM is the first work to introduce EM into MARL. We can theoretically prove that, when using for MARL, SEM has lower space complexity and time complexity than state and action based EM (SAEM), which is originally proposed for single-agent reinforcement learning. Experimental results on StarCraft multi-agent challenge (SMAC) show that introducing episodic memory into MARL can improve sample efficiency and SEM can reduce storage cost and time cost compared with SAEM.

Ab Initio Particle-based Object Manipulation

This paper presents Particle-based Object Manipulation (Prompt), a new approach to robot manipulation of novel objects ab initio, without prior object models or pre-training on a large object data set. The key element of Prompt is a particle-based object representation, in which each particle represents a point in the object, the local geometric, physical, and other features of the point, and also its relation with other particles. Like the model-based analytic approaches to manipulation, the particle representation enables the robot to reason about the object's geometry and dynamics in order to choose suitable manipulation actions. Like the data-driven approaches, the particle representation is learned online in real-time from visual sensor input, specifically, multi-view RGB images. The particle representation thus connects visual perception with robot control. Prompt combines the benefits of both model-based reasoning and data-driven learning. We show empirically that Prompt successfully handles a variety of everyday objects, some of which are transparent. It handles various manipulation tasks, including grasping, pushing, etc,. Our experiments also show that Prompt outperforms a state-of-the-art data-driven grasping method on the daily objects, even though it does not use any offline training data.