Unicorn: Continual Learning with a Universal, Off-policy Agent
Some real-world domains are best characterized as a single task, but for others this perspective is limiting. Instead, some tasks continually grow in complexity, in tandem with the agent's competence. In continual learning, also referred to as lifelong learning, there are no explicit task boundaries or curricula. As learning agents have become more powerful, continual learning remains one of the frontiers that has resisted quick progress. To test continual learning capabilities we consider a challenging 3D domain with an implicit sequence of tasks and sparse rewards. We propose a novel agent architecture called Unicorn, which demonstrates strong continual learning and outperforms several baseline agents on the proposed domain. The agent achieves this by jointly representing and learning multiple policies efficiently, using a parallel off-policy learning setup.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningLifelong learningSimilar Papers 제목 키워드 기반
Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control
Adaptive traffic signal control (ATSC) is crucial in reducing congestion, maximizing throughput, and improving mobility in rapidly growing urban areas. Recent advancements in parameter-sharing multi-agent reinforcement l…
Contrastive LearningMulti-agent Reinforcement LearningTraffic Signal ControlVariational InferenceUnicorn: Scaling High-Dimensional Time Series Forecasting via Universal Correlation Modeling
Modern time series architectures face a fundamental trade-off: channel-independent models scale well with increasing data volume but ignore critical inter-channel dependencies, while channel-dependent models are expressi…
Time Series ForecastingUniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning
Recently, a noticeable trend has emerged in developing pre-trained foundation models in the domains of CV and NLP. However, for molecular pre-training, there lacks a universal model capable of effectively applying to var…
Contrastive LearningDenoisingmolecular representationRepresentation LearningContinual Deep Reinforcement Learning with Task-Agnostic Policy Distillation
Central to the development of universal learning systems is the ability to solve multiple tasks without retraining from scratch when new data arrives. This is crucial because each task requires significant training time.…
Continual LearningDeep Reinforcement Learningreinforcement-learningReinforcement LearningUNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
Commonsense AI has long been seen as a near impossible goal -- until recently. Now, research interest has sharply increased with an influx of new benchmarks and models. We propose two new ways to evaluate commonsense mod…
Common Sense ReasoningHellaSwagKnowledge GraphsQuestion Answering+3