ml-agents

目录树: 7450bd0f

作者	SHA1	备注	提交日期
GitHub	4a7481a1	RayPercpetion, Push Block, and misc environment changes (#432 ) RayPerception moved to a component that is now used by Banana, Soccer, Hallway, and Push Block. Converted Push Block to use RayPerception for local perception and retrained model. Re-worked Hallway to be more extensible.	7 年前
GitHub	976c56c5	Environment Aesthetic Unification (#459 ) * Aesthetic unification * Add new environment images	7 年前
GitHub	c1e930b5	Minor Visual Changes for Environments (#470 ) * Minor changes to ensure a common visual language. * Agents are blue (or additionally red in competitive scenarios). * Interactable objects are orange. * Goals are green when objects, and checkerboards when places. * Not everything perfectly follows this, but things are mostly consistent now. * Renamed "Banana" folder to "BananaCollectors" * Ensured all brains were set to "Player" * Moved non-shared assets out of the "SharedAssets" folder.	7 年前
GitHub	3b866e9f	Use Clipped Gaussian (#649 ) This PR makes the following changes: * Moves clipping of continuous control model into model itself. Output is now always [-1, 1]. * Internal model values are now clipped between [-3, 3] before being rescaled to [-1, 1] for output. * This improves training performance by providing a wider range of values within which the pdf of the gaussian can fall. Output of [-1, 1] is used to be more environment-creator friendly. * Fixes issue where epsilon was erroneously being used to reconstruct old probabilities during PPO update, leading to reduced learning performance. * Introduce ScaleAction() function within python to easily rescale values from [-1, 1] to arbitrary range. * Re-train all CC models using improved algorithm. All performance levels are equal or improved. In the case of Crawler, improvement is drastic. * Update documentation appropriately. * Made miscellaneous minor code style and optimization improvements within environments.	7 年前
GitHub	9ab98584	Additional Environment Variations (#791 ) * Add Visual (Camera) and Imitation Learning variations to example environments	7 年前
GitHub	0c417c55	Release v0.5 (#1202 )	6 年前
Vincent(Yuan) Gao	e8a226a0	Added 3DBall, Banana, Basic, Walker, Hallway and PushBlock (#1312 )	6 年前
vincentpierre	5c060417	Added PushBlock models, fixed trainer config and fixed Learning brain asset (#1344 ) * Added PushBlock models, fixed trainer config and fixed Learning brain asset * Fixed PushBlock model to be in correct place * Added BananaLearning, deleted bytes files for PushBlock, fixed PushBlockLearning.asset * Deleted stray file * Added WallJumpArea training mods * Fixed Banana collector	6 年前
vincentpierre	09657954	Made the default brains of the BananaRL prefab the Player brain	6 年前

9 次代码提交 (7450bd0f-d42c-4bdc-99a8-b0d891640611)