User contributions for Wfisher
Jump to navigation
Jump to search
15 November 2018
- 23:2423:24, 15 November 2018 diff hist +4 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling →Supervised Learning
- 23:2023:20, 15 November 2018 diff hist −3 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling →Self-Play Reinforcement Learning
- 23:1823:18, 15 November 2018 diff hist +1,733 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Add self-play sections
- 22:5722:57, 15 November 2018 diff hist +1,105 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Add information on supervised learning
- 22:5322:53, 15 November 2018 diff hist +58 N File:curling loss function.png Source: http://proceedings.mlr.press/v80/lee18b/lee18b.pdf current
- 22:4222:42, 15 November 2018 diff hist +682 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Start creating supervised learning section
- 22:3022:30, 15 November 2018 diff hist +421 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Finish off MCTS sections
14 November 2018
- 19:3519:35, 14 November 2018 diff hist +934 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Start describing MCTS used
- 19:2219:22, 14 November 2018 diff hist +58 N File:curling kernel equations.png Source: http://proceedings.mlr.press/v80/lee18b/lee18b.pdf current
- 19:1119:11, 14 November 2018 diff hist −42 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Sections
- 19:1119:11, 14 November 2018 diff hist +112 m Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling info on input
- 19:0919:09, 14 November 2018 diff hist +1,082 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Initial network description
- 18:5818:58, 14 November 2018 diff hist +58 N File:curling network layers.png Source: http://proceedings.mlr.press/v80/lee18b/lee18b.pdf current
- 18:4318:43, 14 November 2018 diff hist +243 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Deal with references
- 18:3818:38, 14 November 2018 diff hist +510 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Add to kernel regression
- 18:3718:37, 14 November 2018 diff hist +58 N File:kernel regression.png Source: http://proceedings.mlr.press/v80/lee18b/lee18b.pdf current
- 18:3418:34, 14 November 2018 diff hist +58 N File:gaussian kernel.png Source: http://proceedings.mlr.press/v80/lee18b/lee18b.pdf current
- 18:2418:24, 14 November 2018 diff hist +113 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Add Image for UCT
- 18:2118:21, 14 November 2018 diff hist +85 N File:mcts uct equation.png Equation of UTC for MCTS From: https://www.baeldung.com/java-monte-carlo-tree-search current
- 18:1818:18, 14 November 2018 diff hist +2,036 Deep Reinforcement Learning in Continuous Action Spaces a Case Study in the Game of Simulated Curling Add some MCTS info