Vector-Quantized Vision Foundation Models for Object-Centric Learning

Decomposing visual scenes into objects, as humans do, facilitates modeling object relations and dynamics. Object-Centric Learning (OCL) achieves this by aggregating image or video feature maps into object-level feature vectors, known as \textit{slots}. OCL's self-supervision via reconstructing the input from slots struggles with complex textures, thus many methods employ Vision Foundation Models (VFMs) to extract feature maps with better objectness. However, using VFMs merely as feature extractors does not fully unlock their potential. We propose Vector-Quantized VFMs for OCL (VQ-VFM-OCL, or VVO), where VFM features are extracted to facilitate object-level information aggregation and further quantized to strengthen supervision in reconstruction. Our VVO unifies OCL representatives into a concise architecture. Experiments demonstrate that VVO not only outperforms mainstream methods on object discovery tasks but also benefits downstream tasks like visual prediction and reasoning. The source code is available in the supplement.

Generalist World Model Pre-Training for Efficient Reinforcement Learning

Sample-efficient robot learning is a longstanding goal in robotics. Inspired by the success of scaling in vision and language, the robotics community is now investigating large-scale offline datasets for robot learning. However, existing methods often require expert and/or reward-labeled task-specific data, which can be costly and limit their application in practice. In this paper, we consider a more realistic setting where the offline data consists of reward-free and non-expert multi-embodiment offline data. We show that generalist world model pre-training (WPT), together with retrieval-based experience rehearsal and execution guidance, enables efficient reinforcement learning (RL) and fast task adaptation with such non-curated data. In experiments over 72 visuomotor tasks, spanning 6 different embodiments, covering hard exploration, complex dynamics, and various visual properties, WPT achieves 35.65% and 35% higher aggregated score compared to widely used learning-from-scratch baselines, respectively.

Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning

Offline meta-reinforcement learning aims to equip agents with the ability to rapidly adapt to new tasks by training on data from a set of different tasks. Context-based approaches utilize a history of state-action-reward transitions -- referred to as the context -- to infer representations of the current task, and then condition the agent, i.e., the policy and value function, on the task representations. Intuitively, the better the task representations capture the underlying tasks, the better the agent can generalize to new tasks. Unfortunately, context-based approaches suffer from distribution mismatch, as the context in the offline data does not match the context at test time, limiting their ability to generalize to the test tasks. This leads to the task representations overfitting to the offline training data. Intuitively, the task representations should be independent of the behavior policy used to collect the offline data. To address this issue, we approximately minimize the mutual information between the distribution over the task representations and behavior policy by maximizing the entropy of behavior policy conditioned on the task representations. We validate our approach in MuJoCo environments, showing that compared to baselines, our task representations more faithfully represent the underlying tasks, leading to outperforming prior methods in both in-distribution and out-of-distribution tasks.

Grouped Discrete Representation for Object-Centric Learning

Object-Centric Learning (OCL) can discover objects in images or videos by simply reconstructing the input. For better object discovery, representative OCL methods reconstruct the input as its Variational Autoencoder (VAE) intermediate representation, which suppresses pixel noises and promotes object separability by discretizing continuous super-pixels with template features. However, treating features as units overlooks their composing attributes, thus impeding model generalization; indexing features with scalar numbers loses attribute-level similarities and differences, thus hindering model convergence. We propose \textit{Grouped Discrete Representation} (GDR) for OCL. We decompose features into combinatorial attributes via organized channel grouping, and compose these attributes into discrete representation via tuple indexes. Experiments show that our GDR improves both Transformer- and Diffusion-based OCL methods consistently on various datasets. Visualizations show that our GDR captures better object separability.

Bi-Level Motion Imitation for Humanoid Robots

Imitation learning from human motion capture (MoCap) data provides a promising way to train humanoid robots. However, due to differences in morphology, such as varying degrees of joint freedom and force limits, exact replication of human behaviors may not be feasible for humanoid robots. Consequently, incorporating physically infeasible MoCap data in training datasets can adversely affect the performance of the robot policy. To address this issue, we propose a bi-level optimization-based imitation learning framework that alternates between optimizing both the robot policy and the target MoCap data. Specifically, we first develop a generative latent dynamics model using a novel self-consistent auto-encoder, which learns sparse and structured motion representations while capturing desired motion patterns in the dataset. The dynamics model is then utilized to generate reference motions while the latent representation regularizes the bi-level motion imitation process. Simulations conducted with a realistic model of a humanoid robot demonstrate that our method enhances the robot policy by modifying reference motions to be physically consistent.

Multi-Scale Fusion for Object Representation

Representing images or videos as object-level feature vectors, rather than pixel-level feature maps, facilitates advanced visual tasks. Object-Centric Learning (OCL) primarily achieves this by reconstructing the input under the guidance of Variational Autoencoder (VAE) intermediate representation to drive so-called \textit{slots} to aggregate as much object information as possible. However, existing VAE guidance does not explicitly address that objects can vary in pixel sizes while models typically excel at specific pattern scales. We propose \textit{Multi-Scale Fusion} (MSF) to enhance VAE guidance for OCL training. To ensure objects of all sizes fall within VAE's comfort zone, we adopt the \textit{image pyramid}, which produces intermediate representations at multiple scales; To foster scale-invariance/variance in object super-pixels, we devise \textit{inter}/\textit{intra-scale fusion}, which augments low-quality object super-pixels of one scale with corresponding high-quality super-pixels from another scale. On standard OCL benchmarks, our technique improves mainstream methods, including state-of-the-art diffusion-based ones. The source code is available in the supplemental material.

Organized Grouped Discrete Representation for Object-Centric Learning

Object-Centric Learning (OCL) represents dense image or video pixels as sparse object features. Representative methods utilize discrete representation composed of Variational Autoencoder (VAE) template features to suppress pixel-level information redundancy and guide object-level feature aggregation. The most recent advancement, Grouped Discrete Representation (GDR), further decomposes these template features into attributes. However, its naive channel grouping as decomposition may erroneously group channels belonging to different attributes together and discretize them as sub-optimal template attributes, which losses information and harms expressivity. We propose Organized GDR (OGDR) to organize channels belonging to the same attributes together for correct decomposition from features into attributes. In unsupervised segmentation experiments, OGDR is fully superior to GDR in augmentating classical transformer-based OCL methods; it even improves state-of-the-art diffusion-based ones. Codebook PCA and representation similarity analyses show that compared with GDR, our OGDR eliminates redundancy and preserves information better for guiding object representation learning. The source code is available in the supplementary material.

DeMoBot: Deformable Mobile Manipulation with Vision-based Sub-goal Retrieval

Imitation learning (IL) algorithms typically distill experience into parametric behavior policies to mimic expert demonstrations. Despite their effectiveness, previous methods often struggle with data efficiency and accurately aligning the current state with expert demonstrations, especially in deformable mobile manipulation tasks characterized by partial observations and dynamic object deformations. In this paper, we introduce \textbf{DeMoBot}, a novel IL approach that directly retrieves observations from demonstrations to guide robots in \textbf{De}formable \textbf{Mo}bile manipulation tasks. DeMoBot utilizes vision foundation models to identify relevant expert data based on visual similarity and matches the current trajectory with demonstrated trajectories using trajectory similarity and forward reachability constraints to select suitable sub-goals. Once a goal is determined, a motion generation policy will guide the robot to the next state until the task is completed. We evaluated DeMoBot using a Spot robot in several simulated and real-world settings, demonstrating its effectiveness and generalizability. With only 20 demonstrations, DeMoBot significantly outperforms the baselines, reaching a 50\% success rate in curtain opening and 85\% in gap covering in simulation.

RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands

It has been a long-standing research goal to endow robot hands with human-level dexterity. Bi-manual robot piano playing constitutes a task that combines challenges from dynamic tasks, such as generating fast while precise motions, with slower but contact-rich manipulation problems. Although reinforcement learning based approaches have shown promising results in single-task performance, these methods struggle in a multi-song setting. Our work aims to close this gap and, thereby, enable imitation learning approaches for robot piano playing at scale. To this end, we introduce the Robot Piano 1 Million (RP1M) dataset, containing bi-manual robot piano playing motion data of more than one million trajectories. We formulate finger placements as an optimal transport problem, thus, enabling automatic annotation of vast amounts of unlabeled songs. Benchmarking existing imitation learning approaches shows that such approaches reach state-of-the-art robot piano playing performance by leveraging RP1M.

ROER: Regularized Optimal Experience Replay

Experience replay serves as a key component in the success of online reinforcement learning (RL). Prioritized experience replay (PER) reweights experiences by the temporal difference (TD) error empirically enhancing the performance. However, few works have explored the motivation of using TD error. In this work, we provide an alternative perspective on TD-error-based reweighting. We show the connections between the experience prioritization and occupancy optimization. By using a regularized RL objective with $f-$divergence regularizer and employing its dual form, we show that an optimal solution to the objective is obtained by shifting the distribution of off-policy data in the replay buffer towards the on-policy optimal distribution using TD-error-based occupancy ratios. Our derivation results in a new pipeline of TD error prioritization. We specifically explore the KL divergence as the regularizer and obtain a new form of prioritization scheme, the regularized optimal experience replay (ROER). We evaluate the proposed prioritization scheme with the Soft Actor-Critic (SAC) algorithm in continuous control MuJoCo and DM Control benchmark tasks where our proposed scheme outperforms baselines in 6 out of 11 tasks while the results of the rest match with or do not deviate far from the baselines. Further, using pretraining, ROER achieves noticeable improvement on difficult Antmaze environment where baselines fail, showing applicability to offline-to-online fine-tuning. Code is available at \url{https://github.com/XavierChanglingLi/Regularized-Optimal-Experience-Replay}.