Sample-efficiency in multi-batch reinforcement learning: the need for dimension-dependent adaptivity

Podobne zapisy

• Warm-Starting Networks for Sample-Efficient Continuous Adaptation to Parameter Perturbations in Multi-Agent Reinforcement Learning
  od: Huang, Vivian
  Wydane: (2022)
• Reinforcement learning for robots through efficient simulator sampling
  od: Cutler, Mark Johnson
  Wydane: (2016)
• Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge
  od: Alharbi, Meshal
  Wydane: (2024)
• Learning to teach and meta-learning for sample-efficient multiagent reinforcement learning
  od: Kim, Dong Ki(Aeronautics and astronautics scientist)Massachusetts Institute of Technology.
  Wydane: (2020)
• Optimal convergence rate for exact policy mirror descent in discounted Markov decision processes
  od: Johnson, E, i wsp.
  Wydane: (2023)