Vision-Language-Action (VLA) models have shown great potential in general robotic decision-making tasks via imitation learning. However, the variable quality of training data often constrains the performance of these models. On the other hand, offline Reinforcement Learning (RL) excels at learning robust policy models from mixed-quality data. In this paper, we introduce Reinforced robot GPT (ReinboT), a novel end-to-end VLA model that integrates the RL principle of maximizing cumulative reward. ReinboT achieves a deeper understanding of the data quality distribution by predicting dense returns that capture the nuances of manipulation tasks. The dense return prediction capability enables the robot to generate more robust decision-making actions, oriented towards maximizing future benefits. Extensive experiments show that ReinboT achieves state-of-the-art performance on the CALVIN mixed-quality dataset and exhibits superior few-shot learning and out-of-distribution generalization capabilities in real-world tasks.

The integration of Deep Neural Networks in Reinforcement Learning (RL) systems has led to remarkable progress in solving complex tasks but also introduced challenges like primacy bias and dead neurons. Primacy bias skews learning towards early experiences, while dead neurons diminish the network's capacity to acquire new knowledge. Traditional reset mechanisms aimed at addressing these issues often involve maintaining large replay buffers to train new networks or selectively resetting subsets of neurons. However, these approaches either incur prohibitive computational costs or reset network parameters without ensuring stability through recovery mechanisms, ultimately impairing learning efficiency. In this work, we introduce the novel concept of neuron regeneration, which combines reset mechanisms with knowledge recovery techniques. We also propose a new framework called Sustainable Backup Propagation(SBP) that effectively maintains plasticity in neural networks through this neuron regeneration process. The SBP framework achieves whole network neuron regeneration through two key procedures: cycle reset and inner distillation. Cycle reset involves a scheduled renewal of neurons, while inner distillation functions as a knowledge recovery mechanism at the neuron level. To validate our framework, we integrate SBP with Proximal Policy Optimization (PPO) and propose a novel distillation function for inner distillation. This integration results in Plastic PPO (P3O), a new algorithm that enables efficient cyclic regeneration of all neurons in the actor network. Extensive experiments demonstrate the approach effectively maintains policy plasticity and improves sample efficiency in reinforcement learning.

Offline safe reinforcement learning aims to learn policies that satisfy predefined safety constraints from static datasets. Existing sequence-model-based methods condition action generation on symmetric input tokens for return-to-go and cost-to-go, neglecting their intrinsic asymmetry: RTG serves as a flexible performance target, while CTG should represent a rigid safety boundary. This symmetric conditioning leads to unreliable constraint satisfaction, especially when encountering out-of-distribution cost trajectories. To address this, we propose Boundary-to-Region (B2R), a framework that enables asymmetric conditioning through cost signal realignment . B2R redefines CTG as a boundary constraint under a fixed safety budget, unifying the cost distribution of all feasible trajectories while preserving reward structures. Combined with rotary positional embeddings , it enhances exploration within the safe region. Experimental results show that B2R satisfies safety constraints in 35 out of 38 safety-critical tasks while achieving superior reward performance over baseline methods. This work highlights the limitations of symmetric token conditioning and establishes a new theoretical and practical approach for applying sequence models to safe RL.

Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed data. Although avoiding the time-consuming online interactions in RL, it poses challenges for out-of-distribution (OOD) state actions and often suffers from data inefficiency for training. Despite many efforts being devoted to addressing OOD state actions, the latter (data inefficiency) receives little attention in offline RL. To address this, this paper proposes the cross-domain offline RL, which assumes offline data incorporate additional source-domain data from varying transition dynamics (environments), and expects it to contribute to the offline data efficiency. To do so, we identify a new challenge of OOD transition dynamics, beyond the common OOD state actions issue, when utilizing cross-domain offline data. Then, we propose our method BOSA, which employs two support-constrained objectives to address the above OOD issues. Through extensive experiments in the cross-domain offline RL setting, we demonstrate BOSA can greatly improve offline data efficiency: using only 10% of the target data, BOSA could achieve 74.4% of the SOTA offline RL performance that uses 100% of the target data. Additionally, we also show BOSA can be effortlessly plugged into model-based offline RL and noising data augmentation techniques (used for generating source-domain data), which naturally avoids the potential dynamics mismatch between target-domain data and newly generated source-domain data.

Gradient-based meta-learning (GBML) algorithms can quickly adapt to new tasks by transferring the learned meta-knowledge while assuming that all tasks come from the same distribution (in-distribution, ID). However, in the real world, they often grapple with an out-of-distribution (OOD) generalization challenge, where tasks stem from diverse distributions. OOD exacerbates discrepancies in task gradient magnitudes and directions, posing a formidable challenge for GBML in optimizing meta-knowledge by minimizing the sum of task gradients in each minibatch. To address this problem, we propose RotoGBML, a novel approach designed to homogenize OOD task gradients. RotoGBML employs reweighted vectors to dynamically balance diverse magnitudes to a standardized scale and uses rotation matrices to align conflicting directions. To reduce overhead, we homogenize gradients with the features rather than network parameters. Additionally, to circumvent the impact of non-causal features (e.g., backgrounds), we propose an Invariant Self-Information (ISI) module to extract invariant causal features (e.g., the outlines of objects). Finally, task gradients are homogenized based on these invariant causal features. Experiments demonstrate that RotoGBML outperforms state-of-the-art methods across various few-shot benchmarks.

In this paper, we propose a novel approach called DIffusion-guided DIversity (DIDI) for offline behavioral generation. The goal of DIDI is to learn a diverse set of skills from a mixture of label-free offline data. We achieve this by leveraging diffusion probabilistic models as priors to guide the learning process and regularize the policy. By optimizing a joint objective that incorporates diversity and diffusion-guided regularization, we encourage the emergence of diverse behaviors while maintaining the similarity to the offline data. Experimental results in four decision-making domains (Push, Kitchen, Humanoid, and D4RL tasks) show that DIDI is effective in discovering diverse and discriminative skills. We also introduce skill stitching and skill interpolation, which highlight the generalist nature of the learned skill space. Further, by incorporating an extrinsic reward function, DIDI enables reward-guided behavior generation, facilitating the learning of diverse and optimal behaviors from sub-optimal data.

As a data-driven paradigm, offline reinforcement learning (RL) has been formulated as sequence modeling that conditions on the hindsight information including returns, goal or future trajectory. Although promising, this supervised paradigm overlooks the core objective of RL that maximizes the return. This overlook directly leads to the lack of trajectory stitching capability that affects the sequence model learning from sub-optimal data. In this work, we introduce the concept of max-return sequence modeling which integrates the goal of maximizing returns into existing sequence models. We propose Reinforced Transformer (Reinformer), indicating the sequence model is reinforced by the RL objective. Reinformer additionally incorporates the objective of maximizing returns in the training phase, aiming to predict the maximum future return within the distribution. During inference, this in-distribution maximum return will guide the selection of optimal actions. Empirically, Reinformer is competitive with classical RL methods on the D4RL benchmark and outperforms state-of-the-art sequence model particularly in trajectory stitching ability. Code is public at https://github.com/Dragon-Zhuang/Reinformer.

In this paper, we present ContExtual Imitation Learning (CEIL), a general and broadly applicable algorithm for imitation learning (IL). Inspired by the formulation of hindsight information matching, we derive CEIL by explicitly learning a hindsight embedding function together with a contextual policy using the hindsight embeddings. To achieve the expert matching objective for IL, we advocate for optimizing a contextual variable such that it biases the contextual policy towards mimicking expert behaviors. Beyond the typical learning from demonstrations (LfD) setting, CEIL is a generalist that can be effectively applied to multiple settings including: 1) learning from observations (LfO), 2) offline IL, 3) cross-domain IL (mismatched experts), and 4) one-shot IL settings. Empirically, we evaluate CEIL on the popular MuJoCo tasks (online) and the D4RL dataset (offline). Compared to prior state-of-the-art baselines, we show that CEIL is more sample-efficient in most online IL tasks and achieves better or competitive performances in offline tasks.

In this work, we decouple the iterative bi-level offline RL (value estimation and policy extraction) from the offline training phase, forming a non-iterative bi-level paradigm and avoiding the iterative error propagation over two levels. Specifically, this non-iterative paradigm allows us to conduct inner-level optimization (value estimation) in training, while performing outer-level optimization (policy extraction) in testing. Naturally, such a paradigm raises three core questions that are not fully answered by prior non-iterative offline RL counterparts like reward-conditioned policy: (q1) What information should we transfer from the inner-level to the outer-level? (q2) What should we pay attention to when exploiting the transferred information for safe/confident outer-level optimization? (q3) What are the benefits of concurrently conducting outer-level optimization during testing? Motivated by model-based optimization (MBO), we propose DROP (design from policies), which fully answers the above questions. Specifically, in the inner-level, DROP decomposes offline data into multiple subsets, and learns an MBO score model (a1). To keep safe exploitation to the score model in the outer-level, we explicitly learn a behavior embedding and introduce a conservative regularization (a2). During testing, we show that DROP permits deployment adaptation, enabling an adaptive inference across states (a3). Empirically, we evaluate DROP on various tasks, showing that DROP gains comparable or better performance compared to prior methods.

Few-shot learning aims to generalize to novel classes. It has achieved great success in image and text classification tasks. Inspired by such success, few-shot node classification in homogeneous graph has attracted much attention but few works have begun to study this problem in Heterogeneous Information Network (HIN) so far. We consider few-shot learning in HIN and study a pioneering problem HIN Few-Shot Node Classification (HIN-FSNC) that aims to generalize the node types with sufficient labeled samples to unseen node types with only few-labeled samples. However, existing HIN datasets contain just one labeled node type, which means they cannot meet the setting of unseen node types. To facilitate the investigation of HIN-FSNC, we propose a large-scale academic HIN dataset called HINFShot. It contains 1,235,031 nodes with four node types (author, paper, venue, institution) and all the nodes regardless of node type are divided into 80 classes. Finally, we conduct extensive experiments on HINFShot and the result indicates a significant challenge of identifying novel classes of unseen node types in HIN-FSNC.

Heterogeneous information network (HIN), especially its embedding task, has drawn much attention recently as its rich latent information brings great benefits to complex classification and clustering. Many prior embedding works focus on designing a specific approach for the HIN while others implicitly homogenize the HIN with losing some semantic information. In this paper, a novel explicit homogenization method is proposed to preserve more semantic information, where the latent information of intermediate nodes among each meta-path instance and that among multiple meta-path instances are incorporated into the conventional adjacent matrix (or weight matrix). Then, the transfer of weight matrix and the fusion of node-level embeddings are considered to obtain graph-level embedding to solve the HIN problem. In such way, much more latent information of meta-path is preserved so that the proposed method exhibits its superiority in comparison to state-of-the-art works in classification and clustering tasks.