Uncertainty-aware wind power prediction is essential for grid integration and reliable wind farm operation. We apply neural diffusion processes (NDPs)--a recent class of models that learn distributions over functions--and extend them to a multi-task NDP (MT-NDP) framework for wind power prediction. We provide the first empirical evaluation of NDPs in real supervisory control and data acquisition (SCADA) data. We introduce a task encoder within MT-NDPs to capture cross-turbine correlations and enable few-shot adaptation to unseen turbines. The proposed MT-NDP framework outperforms single-task NDPs and GPs in terms of point accuracy and calibration, particularly for wind turbines whose behaviour deviates from the fleet average. In general, NDP-based models deliver calibrated and scalable predictions suitable for operational deployment, offering sharper, yet trustworthy, predictive intervals that can support dispatch and maintenance decisions in modern wind farms. Introduction Wind energy has become a cornerstone of the global transition to clean power. As wind power capacity expands worldwide, ensuring reliability and minimising downtime are critical to both energy security and the financial viability of wind farms. Beyond energy balancing, uncertainty-aware forecasting also reduces operational uncertainty for wind farm operators, enabling more efficient maintenance scheduling and reducing costly unplanned downtime. This is especially important given that operation and maintenance costs represent a significant share of total expenditure, with unexpected failures making up the largest component [1, 2]. Supervisory control and data acquisition (SCADA) systems provide a low-cost and widely available source of wind turbine data. They capture environmental and operational variables with high frequency, making them invaluable for prediction applications. However, their use is complicated by measurement noise, turbine downtime, and limited public availability [3, 4].

Latent prediction--where agents learn by predicting their own latents--has emerged as a powerful paradigm for training general representations in machine learning. In reinforcement learning (RL), this approach has been explored to define auxiliary losses for a variety of settings, including reward-based and unsupervised RL, behavior cloning, and world modeling. While existing methods are typically limited to single-task learning, one-step prediction, or on-policy trajectory data, we show that temporal difference (TD) learning enables learning representations predictive of long-term latent dynamics across multiple policies from offline, reward-free transitions. Building on this, we introduce TD-JEPA, which leverages TD-based latent-predictive representations into unsupervised RL. TD-JEPA trains explicit state and task encoders, a policy-conditioned multi-step predictor, and a set of parameterized policies directly in latent space. This enables zero-shot optimization of any reward function at test time. Theoretically, we show that an idealized variant of TD-JEPA avoids collapse with proper initialization, and learns encoders that capture a low-rank factorization of long-term policy dynamics, while the predictor recovers their successor features in latent space. Empirically, TD-JEPA matches or outperforms state-of-the-art baselines on locomotion, navigation, and manipulation tasks across 13 datasets in ExoRL and OGBench, especially in the challenging setting of zero-shot RL from pixels.

Recent advancements in imitation learning have led to transformer-based behavior foundation models (BFMs) that enable multi-modal, human-like control for humanoid agents. While excelling at zero-shot generation of robust behaviors, BFMs often require meticulous prompt engineering for specific tasks, potentially yielding suboptimal results. We introduce "Task Tokens", a method to effectively tailor BFMs to specific tasks while preserving their flexibility. Our approach leverages the transformer architecture of BFMs to learn a new task-specific encoder through reinforcement learning, keeping the original BFM frozen. This allows incorporation of user-defined priors, balancing reward design and prompt engineering. By training a task encoder to map observations to tokens, used as additional BFM inputs, we guide performance improvement while maintaining the model's diverse control characteristics. We demonstrate Task Tokens' efficacy across various tasks, including out-of-distribution scenarios, and show their compatibility with other prompting modalities. Our results suggest that Task Tokens offer a promising approach for adapting BFMs to specific control tasks while retaining their generalization capabilities.

Context-based offline meta-reinforcement learning (OMRL) methods have achieved appealing success by leveraging pre-collected offline datasets to develop task representations that guide policy learning. However, current context-based OMRL methods often introduce spurious correlations, where task components are incorrectly correlated due to confounders. These correlations can degrade policy performance when the confounders in the test task differ from those in the training task. To address this problem, we propose CausalCOMRL, a context-based OMRL method that integrates causal representation learning. This approach uncovers causal relationships among the task components and incorporates the causal relationships into task representations, enhancing the generalizability of RL agents. We further improve the distinction of task representations from different tasks by using mutual information optimization and contrastive learning. Utilizing these causal task representations, we employ SAC to optimize policies on meta-RL benchmarks. Experimental results show that CausalCOMRL achieves better performance than other methods on most benchmarks.

Foundation vision-language models have enabled remarkable zero-shot transferability of the pre-trained representations to a wide range of downstream tasks. However, to solve a new task, zero-shot transfer still necessitates human guidance to define visual categories that appear in the data. Here, we show that fully unsupervised transfer emerges when searching for the labeling of a dataset that induces maximal margin classifiers in representation spaces of different foundation models. We present TURTLE, a fully unsupervised method that effectively employs this guiding principle to uncover the underlying labeling of a downstream dataset without any supervision and task-specific representation learning. We evaluate TURTLE on a diverse benchmark suite of 26 datasets and show that it achieves new state-of-the-art unsupervised performance. Furthermore, TURTLE, although being fully unsupervised, outperforms zero-shot transfer baselines on a wide range of datasets. In particular, TURTLE matches the average performance of CLIP zero-shot on 26 datasets by employing the same representation space, spanning a wide range of architectures and model sizes. By guiding the search for the underlying labeling using the representation spaces of two foundation models, TURTLE surpasses zero-shot transfer and unsupervised prompt tuning baselines, demonstrating the surprising power and effectiveness of unsupervised transfer.

Offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance by leveraging pre-collected data and meta-learning techniques. Previous context-based approaches predominantly rely on the intuition that maximizing the mutual information between the task and the task representation ($I(Z;M)$) can lead to performance improvements. Despite achieving attractive results, the theoretical justification of performance improvement for such intuition has been lacking. Motivated by the return discrepancy scheme in the model-based RL field, we find that maximizing $I(Z;M)$ can be interpreted as consistently raising the lower bound of the expected return for a given policy conditioning on the optimal task representation. However, this optimization process ignores the task representation shift between two consecutive updates, which may lead to performance improvement collapse. To address this problem, we turn to use the framework of performance difference bound to consider the impacts of task representation shift explicitly. We demonstrate that by reining the task representation shift, it is possible to achieve monotonic performance improvements, thereby showcasing the advantage against previous approaches. To make it practical, we design an easy yet highly effective algorithm RETRO (\underline{RE}ining \underline{T}ask \underline{R}epresentation shift in context-based \underline{O}ffline meta reinforcement learning) with only adding one line of code compared to the backbone. Empirical results validate its state-of-the-art (SOTA) asymptotic performance, training stability and training-time consumption on MuJoCo and MetaWorld benchmarks.

Despite recent success of deep network-based Reinforcement Learning (RL), it remains elusive to achieve human-level efficiency in learning novel tasks. While previous efforts attempt to address this challenge using meta-learning strategies, they typically suffer from sampling inefficiency with on-policy RL algorithms or meta-overfitting with off-policy learning. In this work, we propose a novel meta-RL strategy to address those limitations. In particular, we decompose the meta-RL problem into three sub-tasks, task-exploration, task-inference and task-fulfillment, instantiated with two deep network agents and a task encoder. During meta-training, our method learns a task-conditioned actor network for task-fulfillment, an explorer network with a self-supervised reward shaping that encourages task-informative experiences in task-exploration, and a context-aware graph-based task encoder for task inference. We validate our approach with extensive experiments on several public benchmarks and the results show that our algorithm effectively performs exploration for task inference, improves sample efficiency during both training and testing, and mitigates the meta-overfitting problem.

Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL are generally similar at a high level. However, most meta-RL methods do not explicitly and adequately model the specific and shared information among different tasks, which limits their ability to learn training tasks and to generalize to novel tasks. In this paper, we propose to capture the shared information on the one hand and meta-learn how to quickly abstract the specific information about a task on the other hand. Methodologically, we train an SGD meta-learner to quickly optimize a task encoder for each task, which generates a task embedding based on past experience. Meanwhile, we learn a policy which is shared across all tasks and conditioned on task embeddings. Empirical results on four simulated tasks demonstrate that our method has better learning capacity on both training and novel tasks and attains up to 3 to 4 times higher returns compared to baselines.