Bahareh Tasdighi

Søgeresultater

• 2024

  Exploring Pessimism and Optimism Dynamics in Deep Reinforcement Learning

  Tasdighi, B., Werge, N., Wu, Y.-S. & Kandemir, M., 6. jun. 2024.

  Publikation: Working paper › Forskning

  Fil

  • Continuous Control 100%
  • Deep Reinforcement Learning 100%
  • Reinforcement Learning 100%
  • Pessimism 100%
  • Function Value 50%
  50 Downloads (Pure)

• Probabilistic Actor-Critic: Learning to Explore with PAC-Bayes Uncertainty

  Tasdighi, B., Werge, N., Wu, Y.-S. & Kandemir, M., 5. feb. 2024.

  Publikation: Working paper › Forskning

  Fil

  • Reinforcement Learning 100%
  • Continuous Control 100%
  • Stochastics 100%
  • Bayesian 100%
  • Prior Art 50%
  43 Downloads (Pure)