Paper

  • Provably Efficient Offline Reinforcement Learning in Regular Decision Processes

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Efficient Offline Reinforcement Learning in Regular Decision Processes

    Roberto Cipollone, Anders Jonsson, Alessandro Ronca, Mohammad Sadegh Talebi p39395-39428 from Advances in Neural Information Processing Systems 36
    Our Price: $0.00
  • Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems

    Masatoshi Uehara, Ayush Sekhari, Jason Lee, Nathan Kallus, Wen Sun p578-592 from Advances in Neural Information Processing Systems 35
    Our Price: $0.00
  • Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation

    Long-Fei Li, Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou p58539-58573 from Advances in Neural Information Processing Systems 37
    Our Price: $0.00
  • Provably Expressive Temporal Graph Networks

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Expressive Temporal Graph Networks

    Amauri Souza, Diego Mesquita, Samuel Kaski, Vikas Garg p32257-32269 from Advances in Neural Information Processing Systems 35
    Our Price: $0.00
  • Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games

    Youbang Sun, Tao Liu, Ruida Zhou, P. R. Kumar, Shahin Shahrampour p43951-43971 from Advances in Neural Information Processing Systems 36
    Our Price: $0.00
  • Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation

    Aniket Das, Dheeraj Nagaraj p49748-49760 from Advances in Neural Information Processing Systems 36
    Our Price: $0.00
  • Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling

    Junyi Li, Heng Huang p70520-70556 from Advances in Neural Information Processing Systems 37
    Our Price: $0.00
  • Provably Feedback-Efficient Reinforcement Learning Via Active Reward Learning

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Feedback-Efficient Reinforcement Learning Via Active Reward Learning

    Dingwen Kong, Lin Yang p11063-11078 from Advances in Neural Information Processing Systems 35
    Our Price: $0.00
  • Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

    Zhihan Liu, Miao Lu, Shenao Zhang, Boyi Liu, Hongyi Guo, Yingxiang Yang, Jose Blanchet, Zhaoran Wang p138663-138697 from Advances in Neural Information Processing Systems 37
    Our Price: $0.00
  • Provably Optimal Memory Capacity for  Modern Hopfield Models:   Transformer-Compatible   Dense Associative Memories as Spherical Codes

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes

    Jerry Yao-Chieh Hu, Dennis Wu, Han Liu p70693-70729 from Advances in Neural Information Processing Systems 37
    Our Price: $0.00
  • Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction

    Xingyu Xu, Yuejie Chi p36148-36184 from Advances in Neural Information Processing Systems 37
    Our Price: $0.00
  • Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards

    Neural Information Processing Systems Foundation, Inc. (NeurIPS)

    Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards

    Semih Cayci, Atilla Eryilmaz p25693-25711 from Advances in Neural Information Processing Systems 36
    Our Price: $0.00