PeopleofSuperintelligence

Videos of Costa Huang

YouTube videos in which Costa Huang speaks or appears, newest first. A model chose them from YouTube search results. List updated 21 October 2026.

  1. Costa Huang, PPO Remastered, 15.Dec.2022Carper AI · 16 December 2022 · 53 min
  2. MuJoCo Gym Environments Running on Apple Silicon via ParallelsCosta Huang · 31 March 2022 · 1 min
  3. Open RL Benchmark by CleanRL 0.5.0 | Reinforcement LearningCosta Huang · 25 April 2021 · 6 min
  4. 1/22/2021 Implementation Week 1 (Batch Constrained Q-Learning (BCQ))Costa Huang · 10 February 2021 · 56 min
  5. 1/22/2021 Literature Week 1 (Batch Constrained Q-Learning (BCQ))Costa Huang · 10 February 2021 · 52 min
  6. 12/11/2020 Implementation Week 2 (Conservative Q-Learning)Costa Huang · 12 December 2020 · 49 min
  7. 12/5/2020 Implementation Week (Conservative Q-Learning)Costa Huang · 7 December 2020 · 1 h
  8. 11/20/2020 Literature Week 3 (Conservative Q-Learning)Costa Huang · 22 November 2020 · 37 min
  9. 11/6/2020 Literature Week 1 (Conservative Q-Learning)Costa Huang · 17 November 2020 · 46 min
  10. 10/23/2020 Implementation Week 2 (Phasic Policy Gradient)Costa Huang · 25 October 2020 · 41 min
  11. [Presentation] Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for RTS GamesCosta Huang · 25 October 2020 · 20 min
  12. 10/16/2020 Implementation Week (Phasic Policy Gradient)Costa Huang · 18 October 2020 · 53 min
  13. 10/9/2020 Literature Week (Phasic Policy Gradient)Costa Huang · 10 October 2020 · 52 min
  14. 6/19/2020 Integration week (PPO with Self-play)Costa Huang · 19 June 2020 · 56 min
  15. 6/12/2020 Implementation Week 2 (PPO with Atari)Costa Huang · 12 June 2020 · 1 h
  16. 6/5/2020 Literature week (PPO with Atari)Costa Huang · 12 June 2020 · 52 min
  17. 5/29/2020 Integration Week (C51)Costa Huang · 2 June 2020 · 48 min
  18. 5/22/2020 Implementation Week 2 (C51)Costa Huang · 23 May 2020 · 51 min
  19. 5/15/2020 Implementation Week 1 (C51)Costa Huang · 20 May 2020 · 1 h
  20. 5/9/2020 Literature Week (C51)Costa Huang · 20 May 2020 · 1 h
  21. 4/17/20 Literature Week (ACER)Costa Huang · 18 April 2020 · 55 min
  22. 4/11/20 TD3 Implementation Week 2Costa Huang · 11 April 2020 · 53 min
  23. 4/3/20 TD3 Implementation Week 1Costa Huang · 4 April 2020 · 55 min
  24. 3/13/2020 TD3 Literature weekCosta Huang · 31 March 2020 · 51 min
  25. 3/13/2020 DDPG Integration weekCosta Huang · 27 March 2020 · 59 min
  26. 3/13/2020 DDPG Implementation WeekCosta Huang · 27 March 2020 · 1 h
  27. 3/6/2020 DDPG Implementation WeekCosta Huang · 12 March 2020 · 59 min
  28. 2/28/19 Literature week (DDPG)Costa Huang · 28 February 2020 · 1 h
  29. 2/21/19 Integration week (PPO code level optimizations)Costa Huang · 24 February 2020 · 1 h
  30. 2/7/19 Implementation week (PPO code level optimizations)Costa Huang · 17 February 2020 · 41 min
  31. Machine Learning Reading Group - Costa Huang, Playing Atari with Deep RLEdward Kim · 10 February 2020 · 1 h
  32. 1/31/19 Implementation week (PPO code level optimizations)Costa Huang · 1 February 2020 · 52 min
  33. 1/24/19 Implementation week (PPO code level optimizations)Costa Huang · 24 January 2020 · 48 min
  34. 1/17/19 Literature week (PPO code level optimizations)Costa Huang · 17 January 2020 · 1 h 6 min
  35. 12/13/2019 Implementation Week 1 Meeting (Soft Actor Critic)Costa Huang · 13 December 2019 · 56 min
  36. 12/6/2019 Literature Week Meeting (Soft Actor Critic)Costa Huang · 6 December 2019 · 57 min
  37. 11/23/2019 First Meeting (Re-recorded)Costa Huang · 25 November 2019 · 45 min
  38. 11/23/2019 First Meeting (Original)Costa Huang · 25 November 2019 · 1 h 16 min
  39. Frame Skipping with Deep Q-Learning as A General TechniqueCosta Huang · 20 March 2019 · 13 min
  40. Project Proposal for CS-613Costa Huang · 19 February 2019 · 5 min
  41. Portwarden Short Demo VideoCosta Huang · 7 December 2018 · 4 min
  42. Portwarden DemoCosta Huang · 4 December 2018 · 9 min

Video data from YouTube API Services. By watching you agree to the YouTube Terms of Service. How we use YouTube data.