Online reinforcement learning (RL) agents increasingly depend on knowledge acquired offline to achieve practical efficiency. Originally studied in offline-to-online RL, this paradigm now spans foundation model post-training and embodied intelligence, with prior types expanding from offline datasets and pre-trained policies to increasingly diverse knowledge sources such as multimodal foundation models and generative world models. Offline priors have become central to how deep RL is developed and deployed. However, this reliance introduces a challenge that the prevailing benchmark-driven paradigm cannot resolve: because prior validity varies across deployments and shifts during training, no single approach to managing it is universally optimal, and benchmark rankings offer limited guidance for real-world deployments. Rather than pursuing universal solutions, we argue that the field should shift to diagnosis-driven tension management, in which deployment-specific evidence guides how the learner relates to its priors throughout training, enabling both flexible and adaptive deployment. We support this position with a framework characterizing how priors reshape online optimization through three functional roles, controlled experiments demonstrating help-or-hurt reversals, cross-domain evidence from foundation model post-training to embodied intelligence, and engagement with five substantive counterarguments.

Residual reinforcement learning (RL) enables stable online refinement of expressive pretrained policies by freezing the base and learning only bounded corrections. However, value learning in residual RL poses unique challenges that remain poorly understood. In this work, we identify two key bottlenecks: cold start pathology, where the critic lacks knowledge of the value landscape around the base policy, and structural scale mismatch, where the residual contribution is dwarfed by the base action. Through systematic investigation, we uncover the mechanisms underlying these bottlenecks, revealing that simple yet principled solutions suffice: base-policy transitions serve as an essential value anchor for implicit warmup, and critic normalization effectively restores representation sensitivity for discerning value differences. Based on these insights, we propose DAWN (Data-Anchored Warmup and Normalization), a minimal approach targeting efficient value learning in residual RL. By addressing these bottlenecks, DAWN demonstrates substantial efficiency gains across diverse benchmarks, policy architectures, and observation modalities.

Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, making it unclear which components are essential for scalability. We revisit this question and argue that the primary driver of scalable multitask RL is not model-based control, but representation learning. In particular, we show that combining predictive, model-based representations with high-capacity value function approximation is sufficient to achieve strong performance, even without planning. We evaluate a simple model-free algorithm, MR.Q, coupled with auxiliary predictive objectives into a scalable actor-critic architecture. This approach outperforms a recent world-model-based method and a range of deep RL baselines across a diverse suite of multitask continuous control tasks, while significantly reducing computational overhead and improving wall-clock efficiency. We observe consistent improvements with increased model capacity and show through ablations that predictive representation learning is critical for performance.

Reinforcement learning systems are significantly more complex than other machine learning paradigms due to inherent properties, causing RL system design to jointly account for many tightly coupled factors. Despite advances in individual algorithmic components, their functional interdependencies remain underexplored: do they exhibit mutual synergy or counterproductive interference? To bridge this gap, we conduct a systematic investigation and find that the efficacy of different components exhibits significant task-dependency, and naively stacking state-of-the-art techniques does not necessarily yield performance gains; instead, it often triggers emergent challenges, such as compounded non-stationarity. Building upon these findings, we distill a suite of actionable insights into the principled coordination of these components. Guided by these insights, we propose ROSER, an RL framework that coordinates three critical dimensions: Model-based Representation, Optimization Stability, and Experience Replay. Across diverse continuous-control benchmarks, ROSER consistently outperforms vanilla baselines and achieves 17.60

Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL), where larger models often degrade performance due to unique optimization pathologies such as plasticity loss. While recent works show that dynamically adapting network topology during training can mitigate these issues, existing studies have three critical limitations: (1) applying uniform dynamic training strategies across all modules despite encoder, critic, and actor following distinct learning paradigms, (2) focusing evaluation on basic architectures without clarifying the relative importance and interaction between dynamic training and architectural improvements, and (3) lacking systematic comparison between different dynamic approaches including sparse-to-sparse, dense-to-sparse, and sparse-to-dense. Through comprehensive investigation across modules and architectures, we reveal that dynamic sparse training strategies provide module-specific benefits that complement the primary scalability foundation established by architectural improvements. We finally distill these insights into Module-Specific Training (MST), a practical framework that further exploits the benefits of architectural improvements and demonstrates substantial scalability gains across diverse RL algorithms without algorithmic modifications.

Effectively scaling up deep reinforcement learning models has proven notoriously difficult due to network pathologies during training, motivating various targeted interventions such as periodic reset and architectural advances such as layer normalization. Instead of pursuing more complex modifications, we show that introducing static network sparsity alone can unlock further scaling potential beyond their dense counterparts with state-of-the-art architectures. This is achieved through simple one-shot random pruning, where a predetermined percentage of network weights are randomly removed once before training. Our analysis reveals that, in contrast to naively scaling up dense DRL networks, such sparse networks achieve both higher parameter efficiency for network expressivity and stronger resistance to optimization challenges like plasticity loss and gradient interference. We further extend our evaluation to visual and streaming RL scenarios, demonstrating the consistent benefits of network sparsity.

This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models. Current models often generate monotonous and simplistic dance sequences that misalign with human preferences because they lack exploration capabilities.The E3D2 framework involves a reward model trained from automatically-ranked dance demonstrations, which then guides the reinforcement learning process. This approach encourages the agent to explore and generate high quality and diverse dance movement sequences. The soundness of the reward model is both theoretically and experimentally validated. Empirical experiments demonstrate the effectiveness of E3D2 on the AIST++ dataset.

Recent advances in visual reinforcement learning (RL) have led to impressive success in handling complex tasks. However, these methods have demonstrated limited generalization capability to visual disturbances, which poses a significant challenge for their real-world application and adaptability. Though normalization techniques have demonstrated huge success in supervised and unsupervised learning, their applications in visual RL are still scarce. In this paper, we explore the potential benefits of integrating normalization into visual RL methods with respect to generalization performance. We find that, perhaps surprisingly, incorporating suitable normalization techniques is sufficient to enhance the generalization capabilities, without any additional special design. We utilize the combination of two normalization techniques, CrossNorm and SelfNorm, for generalizable visual RL. Extensive experiments are conducted on DMControl Generalization Benchmark and CARLA to validate the effectiveness of our method. We show that our method significantly improves generalization capability while only marginally affecting sample efficiency. In particular, when integrated with DrQ-v2, our method enhances the test performance of DrQ-v2 on CARLA across various scenarios, from 14% of the training performance to 97%.

Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL). Although methods like resetting and regularization can potentially mitigate plasticity loss, the influences of various components within the VRL framework on the agent's plasticity are still poorly understood. In this work, we conduct a systematic empirical exploration focusing on three primary underexplored facets and derive the following insightful conclusions: (1) data augmentation is essential in maintaining plasticity; (2) the critic's plasticity loss serves as the principal bottleneck impeding efficient training; and (3) without timely intervention to recover critic's plasticity in the early stages, its loss becomes catastrophic. These insights suggest a novel strategy to address the high replay ratio (RR) dilemma, where exacerbated plasticity loss hinders the potential improvements of sample efficiency brought by increased reuse frequency. Rather than setting a static RR for the entire training process, we propose Adaptive RR, which dynamically adjusts the RR based on the critic's plasticity level. Extensive evaluations indicate that Adaptive RR not only avoids catastrophic plasticity loss in the early stages but also benefits from more frequent reuse in later phases, resulting in superior sample efficiency.

Inverse reinforcement learning (IRL) aims to explicitly infer an underlying reward function based on collected expert demonstrations. Considering that obtaining expert demonstrations can be costly, the focus of current IRL techniques is on learning a better-than-demonstrator policy using a reward function derived from sub-optimal demonstrations. However, existing IRL algorithms primarily tackle the challenge of trajectory ranking ambiguity when learning the reward function. They overlook the crucial role of considering the degree of difference between trajectories in terms of their returns, which is essential for further removing reward ambiguity. Additionally, it is important to note that the reward of a single transition is heavily influenced by the context information within the trajectory. To address these issues, we introduce the Distance-rank Aware Sequential Reward Learning (DRASRL) framework. Unlike existing approaches, DRASRL takes into account both the ranking of trajectories and the degrees of dissimilarity between them to collaboratively eliminate reward ambiguity when learning a sequence of contextually informed reward signals. Specifically, we leverage the distance between policies, from which the trajectories are generated, as a measure to quantify the degree of differences between traces. This distance-aware information is then used to infer embeddings in the representation space for reward learning, employing the contrastive learning technique. Meanwhile, we integrate the pairwise ranking loss function to incorporate ranking information into the latent features. Moreover, we resort to the Transformer architecture to capture the contextual dependencies within the trajectories in the latent space, leading to more accurate reward estimation. Through extensive experimentation, our DRASRL framework demonstrates significant performance improvements over previous SOTA methods.

Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. Notably, employing simple observation transformations alone can yield outstanding performance without extra auxiliary representation tasks or pre-trained encoders. However, it remains unclear which attributes of DA account for its effectiveness in achieving sample-efficient visual RL. To investigate this issue and further explore the potential of DA, this work conducts comprehensive experiments to assess the impact of DA's attributes on its efficacy and provides the following insights and improvements: (1) For individual DA operations, we reveal that both ample spatial diversity and slight hardness are indispensable. Building on this finding, we introduce Random PadResize (Rand PR), a new DA operation that offers abundant spatial diversity with minimal hardness. (2) For multi-type DA fusion schemes, the increased DA hardness and unstable data distribution result in the current fusion schemes being unable to achieve higher sample efficiency than their corresponding individual operations. Taking the non-stationary nature of RL into account, we propose a RL-tailored multi-type DA fusion scheme called Cycling Augmentation (CycAug), which performs periodic cycles of different DA operations to increase type diversity while maintaining data distribution consistency. Extensive evaluations on the DeepMind Control suite and CARLA driving simulator demonstrate that our methods achieve superior sample efficiency compared with the prior state-of-the-art methods.