Reinforcement Learning
Multi-agent Dynamic Algorithm Configuration
Unlike AC, DAC can dynamically adjust the algorithm's configuration during
Large-ScaleRetrievalforReinforcementLearning
Thisallows agents to directly learn in an end-to-end manner to utilise relevant information to inform their outputs. In addition, new information can be attended to by the agent, without retraining, by simply augmenting the retrieval dataset.
Large-ScaleRetrievalforReinforcementLearning
Thisallows agents to directly learn in an end-to-end manner to utilise relevant information to inform their outputs. In addition, new information can be attended to by the agent, without retraining, by simply augmenting the retrieval dataset.
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
Work done as a visiting student at MIT. 38th Conference on Neural Information Processing Systems (NeurIPS 2024).
Finite-TimeAnalysisofAdaptiveTemporalDifference LearningwithDeepNeuralNetworks
Nevertheless, theperformance guarantee of adaptive TD with neural network approximation remains widely unknown.
