Paper proposes a method to compose task-agnostic skills for solving new problems.
problem Learning task-specific policies for solving new problems.
method Deep reinforcement learning-based skill transfer and composition method.
result Method transfers skills to new problem settings and solves challenging environments with high data efficiency.
Proposes learning task-agnostic dynamics priors for faster RL.
problem Challenges in learning accurate dynamics models for RL.
method Pre-training a frame predictor on physics videos to initialize and fine-tune dynamics models.
result Improves policy learning and convergence, outperforming competitors.
Paper proposes a policy-search algorithm to learn entropy-maximizing exploration policies in reward-free environments.
problem Reward-free learning in high-dimensional, continuous-control domains.
method Maximum Entropy POLicy optimization (MEPOL) algorithm that maximizes a non-parametric state entropy estimate.
result MEPOL learns a maximum-entropy exploration policy that facilitates learning various reward-based tasks.
Task-agnostic RL tackles exploration in MDPs with multiple tasks.
problem Challenges in reinforcement learning with multiple tasks or conflicting objectives.
method Task-agnostic RL framework, UCBZero algorithm.
result UCBZero finds near-optimal policies for multiple tasks efficiently.
New method learns robot actions from videos without explicit labels.
problem Training robots to perform tasks from few demonstrations.
method Uses images and text for task-agnostic and general representation, synthesizes hallucinated actions, and applies dense correspondences.
result Trains robot policies solely from RGB videos, achieving diverse tasks across different robots and environments.
Generically learns movement control policies from exploration data.
problem Movement optimization in physically based characters.
method Parameterizes actions as target states, learns low-level control policy.
result Improves movement optimization across multiple tasks and algorithms.
This study optimizes offline reinforcement learning methods for various tasks without rewards.
problem Optimizing offline reinforcement learning for multiple tasks without rewards.
method Designing a new model-based approach with singleton absorbing MDPs to achieve optimal convergence rates.
result Achieved optimal convergence rates for offline reinforcement learning in various settings.
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances …
The paper proposes an algorithm to learn efficient and effective exploration policies in reinforcement learning.
problem Balancing exploration and exploitation in reinforcement learning.
method Formalized a counterfactual metric for exploration utility and used meta-learning to learn an end-to-end exploration policy.
result Demonstrated improved performance in high-dimensional control tasks in MuJoCo simulator compared to previous methods.
This work evaluates task-agnostic exploration methods for fixed-batch learning.
problem Expensive real-world experience for robotics tasks.
method Fixed datasets for arbitrary task learning.
result Improved offline learning for robotics tasks.
Task-agnostic data augmentation shows little benefit for pretrained transformers.
problem Evaluating the effectiveness of task-agnostic data augmentation on pretrained transformers.
method Conducted a systematic examination of two data augmentation techniques (Easy Data Augmentation and Back-Translation) across 5 tasks, 6 datasets, and 3 pretrained transformer models.
result Data augmentation techniques previously effective for non-pretrained models fail to consistently improve performance for pretrained transformers, even with limited training data.
New method prevents forgetting in learning new tasks.
problem Learning new tasks without forgetting old knowledge.
method Hierarchical information-theoretic optimality principle and Mixture-of-Variational-Experts layer.
result Our method can operate task-agnostically and improve performance in various learning problems.
Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the knowledge learned across many tasks as an inductive bias towards better natural languag…
Improved cooperation between levels boosts reinforcement learning performance.
problem Training multi-level policies in hierarchical reinforcement learning.
method Modeling policy optimization as a multi-agent process and inducing cooperation between sub-policies.
result Inducing cooperation between sub-policies leads to stronger and more sample-efficient policies.
CUDC collects diverse data for offline RL by predicting future states.
problem Challenges in collecting task-agnostic data for offline RL.
method Adaptive temporal distances for curiosity-driven data collection.
result CUDC outperforms existing unsupervised methods in offline RL tasks.
TAME learns new tasks without knowing them, outperforming existing methods.
problem Learning new tasks without task identities.
method TAME detects task shifts using loss function deviations and employs online pruning.
result TAME outperforms existing methods on continual learning benchmarks.
Paper introduces TrufLL for language model training without labeled data.
problem Training language models from scratch with reinforcement learning.
method Dynamic vocabulary truncation in RL for language generation.
result TrufLL successfully learns language generation policies from scratch.
Task-agnostic data valuation without validation requirements.
problem Valuing data without specific task assumptions.
method Estimating data diversity and relevance through queries without raw data.
result Estimates capture the diversity and relevance of seller's data for the buyer.
New method learns belief representations for GAIL in POMDPs.
problem Imitation learning in partially observable Markov decision processes (POMDPs).
method Joint learning of belief module and policy with task-aware imitation loss and belief regularization.
result Our BMIL approach outperforms GAIL and task-agnostic belief learning.
MTL-NAS combines NAS with GP-MTL for task-agnostic multi-task learning.
problem Designing architectures for diverse tasks with varying priors.
method Disentangled GP-MTL networks, hierarchical feature sharing, and gradient-based search.
result General-purpose model trained once can adapt to multiple tasks.
Catastrophic forgetting is the notorious vulnerability of neural networks to the change of the data distribution while learning. This phenomenon has long been considered a major obstacle for allowing the use of learning agents in realistic continual learning settings. A large body of continual learning research assumes…
Tool manipulation is vital for facilitating robots to complete challenging task goals. It requires reasoning about the desired effect of the task and thus properly grasping and manipulating the tool to achieve the task. Task-agnostic grasping optimizes for grasp robustness while ignoring crucial task-specific constrain…
New method handles unknown task boundaries in continual learning.
problem Catastrophic forgetting in neural networks.
method Fixed-point equations for online variational Bayes optimization.
result Approximates online Bayes update for non-stationary data.
TA-VAAL improves active learning by better utilizing task structures and overall data distribution.
problem High labeling cost limits deep learning applications; active learning selects informative samples.
method Task-aware variational adversarial active learning (TA-VAAL) modifies VAAL by relaxing task loss prediction and using ranking loss information.
result TA-VAAL outperforms state-of-the-arts on various datasets, including balanced and imbalanced labels.
PeL separates sensory interface optimization from decision learning.
problem Optimizing sensory interfaces without task-specific information.
method Formal separation of perception and decision learning, using metrics for stability, informativeness, and geometry.
result Updates preserving invariants are orthogonal to decision gradients.
New method improves learning speed without knowing task boundaries.
problem Catastrophic forgetting in non-stationary data.
method Meta learning for task agnostic continual learning.
result Faster recovery of performance in unseen tasks.
Paper proposes a method to make learned models focus on task-relevant information.
problem Mismatch between model objective and downstream task objective.
method Direct prediction towards task-relevant information, self-supervised.
result Model more effectively models relevant parts of the scene conditioned on the goal.
Novel framework for ML-assisted inference valid for any statistical task.
problem Limited validity of existing methods for post-prediction inference.
method Introduces PSPS framework for task-agnostic ML-assisted inference.
result Valid and efficient inference for arbitrary ML models.
The paper proposes an algorithm to learn causal state representations for partially observable environments.
problem Learning task-agnostic state abstractions in partially observable environments.
method The approach involves learning approximate causal state representations from RNNs trained to predict observations given the history.
result The learned state representations are useful for efficient policy learning in reinforcement learning problems with rich observation spaces.
A graph abstraction speeds up reinforcement learning in complex environments.
problem Learning hierarchical reinforcement learning tasks in complex environments.
method Jointly trains a latent pivotal state model and a curiosity-driven policy. Uses a world graph to guide high-level and low-level agents.
result Significant performance and efficiency improvements over baseline methods.
New method prevents forgetting in learning new tasks.
problem Poor ability of models to solve new problems without forgetting.
method Task-agnostic hierarchical information-theoretic optimality principle with Mixture-of-Variational-Experts layer.
result Demonstrated competitive performance in continual supervised and reinforcement learning.
Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a meta-learner could be fragile when it is over-trained on existing tasks during …
New algorithm optimizes exploration in unknown MDPs.
problem Optimal exploration in unknown Markov decision processes.
method Trajectory-optimization-based approximate solution using Bayesian experimental design.
result Empirically superior to intrinsic-motivation-based algorithms in convergence and model fidelity.
Improved model-based reinforcement learning for multi-agent Markov games.
problem Suboptimal sample complexity for model-based algorithms in multi-agent reinforcement learning.
method Optimistic Nash Value Iteration (Nash-VI) for two-player zero-sum Markov games.
result First model-based algorithm matching information-theoretic lower bound with improved sample complexity.
This paper tackles online reinforcement learning for unseen tasks with unknown boundaries.
problem Real-world tasks violate assumptions of task distributions, independence, and clear task delineations.
method A mixture of Gaussian Processes models different dynamics, and a transition prior handles temporal dependencies.
result The approach reliably handles task distribution shifts and outperforms alternatives in non-stationary tasks.
Meta-learning approach prevents forgetting across tasks.
problem Catastrophic forgetting in deep neural networks.
method Incremental Task-Agnostic Meta-learning (iTAML) with a meta-update rule.
result Significant improvements in class-incremental learning tasks.
Study breaks down graphs into structural and featural components for task-agnostic data valuation.
problem Lack of methods to assess the value of graphs in data marketplaces.
method Introduces blind message passing framework to evaluate graphs without specific task metrics.
result Demonstrates effectiveness in capturing structural disparities, relevance, and diversity of seller data for buyers.
Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of biological memory transfer to arrive at AI algorithms for memory consolidation and repl…
Big models pretrain and fine-tune for semi-supervised learning on ImageNet.
problem Learning from few labeled examples with a large amount of unlabeled data.
method Unsupervised pretraining of a big ResNet model followed by supervised fine-tuning and distillation.
result 73.9% ImageNet top-1 accuracy with just 1% of labels (≤13 labeled images per class). Theory explains how AI models can predict unseen tasks without labeled data.
problem Understanding how AI models can generalize to unseen tasks.
method Developed a theoretical framework to analyze zero-shot prediction.
result Identified key quantities and independence relationships for generalization.
New RL approach speeds up training across tasks.
problem Training reinforcement learning models quickly and efficiently.
method Combines planning quasi-metric and task-specific aimers.
result Achieves multiple-fold speed-up on bit-flip and robotic arm tasks.
Efficient text classification model reduces size and speeds up inference.
problem Label-scarce conditions in text classification.
method Convolutional student architecture trained by distillation from a transformer teacher.
result 300x inference speedup and 39x reduction in parameter count.
The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original pro…
Efficient exploration is an unsolved problem in Reinforcement Learning which is usually addressed by reactively rewarding the agent for fortuitously encountering novel situations. This paper introduces an efficient active exploration algorithm, Model-Based Active eXploration (MAX), which uses an ensemble of forward mod…
Paper analyzes consistency between neural networks at different levels.
problem Understanding knowledge consistency between neural networks.
method Generic definition and task-agnostic method to disentangle consistent knowledge.
result Knowledge consistency provides new insights and can improve network performance.
dGAP learns feature dependencies and predicts targets simultaneously.
problem Learning task-agnostic statistical dependencies and missing explicit feature dependencies.
method Jointly optimizes a neural dependency graph and target prediction loss.
result dGAP can recover correct feature dependencies and improve prediction accuracy.
In this paper, we focus on weakly supervised learning with noisy training data for both classification and regression problems.We assume that the training outputs are collected from a mixture of a target and correlated noise distributions.Our proposed method simultaneously estimates the target distribution and the qual…
Semantic segmentation remains a computationally intensive algorithm for embedded deployment even with the rapid growth of computation power. Thus efficient network design is a critical aspect especially for applications like automated driving which requires real-time performance. Recently, there has been a lot of resea…