diff --git a/Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBall.nn b/Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBall.nn index 36b297ed87..67c1814a87 100644 Binary files a/Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBall.nn and b/Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBall.nn differ diff --git a/Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallHard.nn b/Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallHard.nn index 1509e729aa..ff298283ff 100644 Binary files a/Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallHard.nn and b/Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallHard.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Basic/TFModels/Basic.nn b/Project/Assets/ML-Agents/Examples/Basic/TFModels/Basic.nn index be7486985f..ed5f41d94b 100644 Binary files a/Project/Assets/ML-Agents/Examples/Basic/TFModels/Basic.nn and b/Project/Assets/ML-Agents/Examples/Basic/TFModels/Basic.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Bouncer/TFModels/Bouncer.nn b/Project/Assets/ML-Agents/Examples/Bouncer/TFModels/Bouncer.nn index ad0c84cf3f..40645ace67 100644 Binary files a/Project/Assets/ML-Agents/Examples/Bouncer/TFModels/Bouncer.nn and b/Project/Assets/ML-Agents/Examples/Bouncer/TFModels/Bouncer.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerDynamic.nn b/Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerDynamic.nn index 61a5c3b700..1ffebb1b79 100644 Binary files a/Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerDynamic.nn and b/Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerDynamic.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerStatic.nn b/Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerStatic.nn index 040fa9faf7..738e09a0cb 100644 Binary files a/Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerStatic.nn and b/Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerStatic.nn differ diff --git a/Project/Assets/ML-Agents/Examples/FoodCollector/TFModels/FoodCollector.nn b/Project/Assets/ML-Agents/Examples/FoodCollector/TFModels/FoodCollector.nn index f28c6b665c..e7bf8eaf1e 100644 Binary files a/Project/Assets/ML-Agents/Examples/FoodCollector/TFModels/FoodCollector.nn and b/Project/Assets/ML-Agents/Examples/FoodCollector/TFModels/FoodCollector.nn differ diff --git a/Project/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorld.nn b/Project/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorld.nn index 68b8fb1633..58859d9942 100644 Binary files a/Project/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorld.nn and b/Project/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorld.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Hallway/TFModels/Hallway.nn b/Project/Assets/ML-Agents/Examples/Hallway/TFModels/Hallway.nn index ad55a04cb7..cbecefc47e 100644 Binary files a/Project/Assets/ML-Agents/Examples/Hallway/TFModels/Hallway.nn and b/Project/Assets/ML-Agents/Examples/Hallway/TFModels/Hallway.nn differ diff --git a/Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlock.nn b/Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlock.nn index d27868ca3b..16ab78e36e 100644 Binary files a/Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlock.nn and b/Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlock.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Pyramids/TFModels/Pyramids.nn b/Project/Assets/ML-Agents/Examples/Pyramids/TFModels/Pyramids.nn index fb15b26d27..0262870295 100644 Binary files a/Project/Assets/ML-Agents/Examples/Pyramids/TFModels/Pyramids.nn and b/Project/Assets/ML-Agents/Examples/Pyramids/TFModels/Pyramids.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Reacher/TFModels/Reacher.nn b/Project/Assets/ML-Agents/Examples/Reacher/TFModels/Reacher.nn index aaac26a96e..9bca760a4c 100644 Binary files a/Project/Assets/ML-Agents/Examples/Reacher/TFModels/Reacher.nn and b/Project/Assets/ML-Agents/Examples/Reacher/TFModels/Reacher.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Soccer/TFModels/Soccer.nn b/Project/Assets/ML-Agents/Examples/Soccer/TFModels/Soccer.nn index 9cb8d39346..320eccb5a4 100644 Binary files a/Project/Assets/ML-Agents/Examples/Soccer/TFModels/Soccer.nn and b/Project/Assets/ML-Agents/Examples/Soccer/TFModels/Soccer.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Tennis/TFModels/Tennis.nn b/Project/Assets/ML-Agents/Examples/Tennis/TFModels/Tennis.nn index f0bc1351d8..681cadfc64 100644 Binary files a/Project/Assets/ML-Agents/Examples/Tennis/TFModels/Tennis.nn and b/Project/Assets/ML-Agents/Examples/Tennis/TFModels/Tennis.nn differ diff --git a/Project/Assets/ML-Agents/Examples/Walker/TFModels/Walker.nn b/Project/Assets/ML-Agents/Examples/Walker/TFModels/Walker.nn index 15cd9ffbae..25664ded29 100644 Binary files a/Project/Assets/ML-Agents/Examples/Walker/TFModels/Walker.nn and b/Project/Assets/ML-Agents/Examples/Walker/TFModels/Walker.nn differ diff --git a/Project/Assets/ML-Agents/Examples/WallJump/TFModels/BigWallJump.nn b/Project/Assets/ML-Agents/Examples/WallJump/TFModels/BigWallJump.nn index a6d5be6666..cf4e7bc3f2 100644 Binary files a/Project/Assets/ML-Agents/Examples/WallJump/TFModels/BigWallJump.nn and b/Project/Assets/ML-Agents/Examples/WallJump/TFModels/BigWallJump.nn differ diff --git a/Project/Assets/ML-Agents/Examples/WallJump/TFModels/SmallWallJump.nn b/Project/Assets/ML-Agents/Examples/WallJump/TFModels/SmallWallJump.nn index 3452a7c213..654a1243b9 100644 Binary files a/Project/Assets/ML-Agents/Examples/WallJump/TFModels/SmallWallJump.nn and b/Project/Assets/ML-Agents/Examples/WallJump/TFModels/SmallWallJump.nn differ diff --git a/README.md b/README.md index 2db63afc96..9cb0afec0d 100644 --- a/README.md +++ b/README.md @@ -29,14 +29,14 @@ developer communities. * Unity environment control from Python * 15+ sample Unity environments * Two deep reinforcement learning algorithms, -[Proximal Policy Optimization](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Training-PPO.md) - (PPO) and [Soft Actor-Critic](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Training-SAC.md) +[Proximal Policy Optimization](docs/Training-PPO.md) + (PPO) and [Soft Actor-Critic](docs/Training-SAC.md) (SAC) * Support for multiple environment configurations and training scenarios * Self-play mechanism for training agents in adversarial scenarios * Train memory-enhanced agents using deep reinforcement learning * Easily definable Curriculum Learning and Generalization scenarios -* Built-in support for [Imitation Learning](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Training-Imitation-Learning.md) through Behavioral Cloning or Generative Adversarial Imitation Learning +* Built-in support for [Imitation Learning](docs/Training-Imitation-Learning.md) through Behavioral Cloning or Generative Adversarial Imitation Learning * Flexible agent control with On Demand Decision Making * Visualizing network outputs within the environment * Wrap learning environments as a gym @@ -46,6 +46,7 @@ developer communities. ## Releases & Documentation **Our latest, stable release is 0.15.0. Click [here](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Readme.md) to + get started with the latest release of ML-Agents.** The table below lists all our releases, including our `master` branch which is under active