pith. sign in

Philip S. Thomas

Identifiers

  • name variant Philip S. Thomas 0.60 · backfill

Papers (15)

  1. Classical Policy Gradient: Preserving Bellman's Principle of Optimality cs.LG · 2019 · author #1
  2. A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning cs.LG · 2019 · author #2
  3. Learning Action Representations for Reinforcement Learning cs.LG · 2019 · author #5
  4. Privacy Preserving Off-Policy Evaluation cs.LG · 2019 · author #2
  5. Natural Option Critic cs.LG · 2018 · author #2
  6. A Compression-Inspired Framework for Macro Discovery cs.AI · 2017 · author #3
  7. On Ensuring that Intelligent Machines Are Well-Behaved cs.AI · 2017 · author #1
  8. Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines cs.AI · 2017 · author #1
  9. Data-Efficient Policy Evaluation Through Behavior Policy Search cs.AI · 2017 · author #2
  10. Decoupling Learning Rules from Representations cs.AI · 2017 · author #1
  11. Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation cs.AI · 2017 · author #2
  12. Importance Sampling with Unequal Support cs.LG · 2016 · author #1
  13. Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning cs.LG · 2016 · author #1
  14. A Notation for Markov Decision Processes cs.AI · 2015 · author #1
  15. Increasing the Action Gap: New Operators for Reinforcement Learning cs.AI · 2015 · author #4

Mentions

  • 1711.09048 #3 · arxiv_oai · confidence 0.70 Philip S. Thomas

Frequent Coauthors