In meta-learning and its downstream tasks, many methods rely on implicit adaptation to task variations, where multiple factors are mixed together in a single entangled representation. This makes it difficult to interpret which factors drive performance and can hinder generalization. In this work, we introduce a disentangled multi-context meta-learning framework that explicitly assigns each task factor to a distinct context vector. By decoupling these variations, our approach improves robustness through deeper task understanding and enhances generalization by enabling context vector sharing across tasks with shared factors. We evaluate our approach in two domains. First, on a sinusoidal regression task, our model outperforms baselines on out-of-distribution tasks and generalizes to unseen sine functions by sharing context vectors associated with shared amplitudes or phase shifts. Second, in a quadruped robot locomotion task, we disentangle the robot-specific properties and the characteristics of the terrain in the robot dynamics model. By transferring disentangled context vectors acquired from the dynamics model into reinforcement learning, the resulting policy achieves improved robustness under out-of-distribution conditions, surpassing the baselines that rely on a single unified context. Furthermore, by effectively sharing context, our model enables successful sim-to-real policy transfer to challenging terrains with out-of-distribution robot-specific properties, using just 20 seconds of real data from flat terrain, a result not achievable with single-task adaptation.

The robotics research field lacks formalized definitions and frameworks for evaluating advanced capabilities including generalizability (the ability for robots to perform tasks under varied contexts) and reproducibility (the performance of a reproduced robot capability in different labs under the same experimental conditions). This paper presents an initial conceptual framework, MIRRER, that unites the concepts of performance evaluation, benchmarking, and reproduced/replicated experimentation in order to facilitate comparable robotics research. Several open issues with the application of the framework are also presented.

C-Procgen provides access to over 200 unique game contexts across 16 games. It allows for detailed configuration of environments, ranging from game mechanics to agent attributes. This makes the procedural generation process, previously a black-box in Procgen, more transparent and adaptable for various research needs. The upgrade enhances dynamic context management and individualized assignments, while maintaining computational efficiency. C-Procgen's controllable contexts make it applicable in diverse reinforcement learning research areas, such as learning dynamics analysis, curriculum learning, and transfer learning. We believe that C-Procgen will fill a gap in the current literature and offer a valuable toolkit for future works.

Recent literature has explored various ways to improve soft sensors using learning algorithms with transferability. Broadly put, the performance of a soft sensor may be strengthened when it is learned by solving multiple tasks. The usefulness of transferability depends on how strongly related the devised learning tasks are. A particularly relevant case for transferability, is when a soft sensor is to be developed for a process of which there are many realizations, e.g. system or device with many implementations from which data is available. Then, each realization presents a soft sensor learning task, and it is reasonable to expect that the different tasks are strongly related. Applying transferability in this setting leads to what we call multi-unit soft sensing, where a soft sensor models a process by learning from data from all of its realizations. This paper explores the learning abilities of a multi-unit soft sensor, which is formulated as a hierarchical model and implemented using a deep neural network. In particular, we investigate how well the soft sensor generalizes as the number of units increase. Using a large industrial dataset, we demonstrate that, when the soft sensor is learned from a sufficient number of tasks, it permits few-shot learning on data from new units. Surprisingly, regarding the difficulty of the task, few-shot learning on 1-3 data points often leads to a high performance on new units.

We hypothesize that taking advantage of prior knowledge about the underlying Figure 1: Workflow diagram for an existing self-paced RL task structure can improve the effectiveness approach, and two methods that we propose: intermediate of self-paced RL. We develop a self-paced RL self-paced RL and reward-machine-guided, self-paced RL. algorithm guided by reward machines, i.e., a type of finite-state machine that encodes the underlying task structure. The algorithm integrates reward machines in 1) the update of the policy and value et al. [2017] focus on automating the process of curriculum functions obtained by any RL algorithm of choice, generation. Klink et al. [2020a] adopt self-paced learning and 2) the update of the automated curriculum that [Kumar et al., 2010] in RL by developing an algorithm that generates context distributions. Our empirical results creates a sequence of probability distributions over contexts evidence that the proposed algorithm achieves [Hallak et al., 2015]. The dynamics, the reward function, optimal behavior reliably even in cases in which and the initial state distribution of an environment change existing baselines cannot make any meaningful with respect to the context. Given a target context distribution, progress. It also decreases the curriculum length a self-paced RL algorithm iteratively generates context and reduces the variance in the curriculum generation distributions that maximizes the expected discounted return, process by up to one-fourth and four orders of regularized by the Kullback-Leibler (KL) divergence from magnitude, respectively.

The objective of this work is to augment the basic abilities of a robot by learning to use new sensorimotor primitives to solve complex long-horizon manipulation problems. This requires flexible generative planning that can combine primitive abilities in novel combinations and thus generalize across a wide variety of problems. In order to plan with primitive actions, we must have models of the preconditions and effects of those actions: under what circumstances will executing this primitive successfully achieve some particular effect in the world? We use, and develop novel improvements on, state-of-the-art methods for active learning and sampling. We use Gaussian process methods for learning the conditions of operator effectiveness from small numbers of expensive training examples. We develop adaptive sampling methods for generating a comprehensive and diverse sequence of continuous parameter values (such as pouring waypoints for a cup) configurations and during planning for solving a new task, so that a complete robot plan can be found as efficiently as possible. We demonstrate our approach in an integrated system, combining traditional robotics primitives with our newly learned models using an efficient robot task and motion planner. We evaluate our approach both in simulation and in the real world through measuring the quality of the selected pours and scoops. Finally, we apply our integrated system to a variety of long-horizon simulated and real-world manipulation problems.

We propose CAML, a meta-learning method for fast adaptation that partitions the model parameters into two parts: context parameters that serve as additional input to the model and are adapted on individual tasks, and shared parameters that are meta-trained and shared across tasks. At test time, the context parameters are updated with one or several gradient steps on a task-specific loss that is backpropagated through the shared part of the network. Compared to approaches that adjust all parameters on a new task (e.g., MAML), our method can be scaled up to larger networks without overfitting on a single task, is easier to implement, and saves memory writes during training and network communication at test time for distributed machine learning systems. We show empirically that this approach outperforms MAML, is less sensitive to the task-specific learning rate, can capture meaningful task embeddings with the context parameters, and outperforms alternative partitionings of the parameter vectors. A key challenge in meta-learning is fast adaptation: learning on previously unseen tasks fast and with little data. In principle, this can be achieved by leveraging knowledge obtained in other, related tasks. However, the best way to do so remains an open question. A popular recent method for fast adaptation is model agnostic meta learning (MAML) (Finn et al., 2017a), which learns a model initialisation, such that at test time the model can be adapted to solve the new task in only a few gradient steps. MAML has an interleaved training procedure, comprised of inner loop and outer loop updates that operate on a batch of tasks at each iteration. In the inner loop, MAML learns task-specific parameters by performing one gradient step on a task-specific loss.