diff --git a/Project/Assets/ML-Agents/Examples/Match3/TFModels/Match3VectorObsSmallerBatch.onnx b/Project/Assets/ML-Agents/Examples/Match3/TFModels/Match3VectorObsSmallerBatch.onnx new file mode 100644 index 00000000000..fff1633ac94 Binary files /dev/null and b/Project/Assets/ML-Agents/Examples/Match3/TFModels/Match3VectorObsSmallerBatch.onnx differ diff --git a/Project/Assets/ML-Agents/Examples/Match3/TFModels/Match3VectorObsSmallerBatch.onnx.meta b/Project/Assets/ML-Agents/Examples/Match3/TFModels/Match3VectorObsSmallerBatch.onnx.meta new file mode 100644 index 00000000000..fc7d9f32040 --- /dev/null +++ b/Project/Assets/ML-Agents/Examples/Match3/TFModels/Match3VectorObsSmallerBatch.onnx.meta @@ -0,0 +1,14 @@ +fileFormatVersion: 2 +guid: 25939cbd8e259bb44b9dcd13f37420cb +ScriptedImporter: + fileIDToRecycleName: + 11400000: main obj + 11400002: model data + externalObjects: {} + userData: + assetBundleName: + assetBundleVariant: + script: {fileID: 11500000, guid: 683b6cb6d0a474744822c888b46772c9, type: 3} + optimizeModel: 1 + forceArbitraryBatchSize: 1 + treatErrorsAsWarnings: 0 diff --git a/config/ppo/Match3.yaml b/config/ppo/Match3.yaml index e60a138cfa1..ac370282e84 100644 --- a/config/ppo/Match3.yaml +++ b/config/ppo/Match3.yaml @@ -2,18 +2,18 @@ behaviors: Match3VectorObs: trainer_type: ppo hyperparameters: - batch_size: 64 - buffer_size: 12000 + batch_size: 16 + buffer_size: 120 learning_rate: 0.0003 - beta: 0.001 + beta: 0.005 epsilon: 0.2 lambd: 0.99 num_epoch: 3 - learning_rate_schedule: constant + learning_rate_schedule: linear network_settings: normalize: true - hidden_units: 128 - num_layers: 2 + hidden_units: 256 + num_layers: 4 vis_encode_type: match3 reward_signals: extrinsic: @@ -21,7 +21,7 @@ behaviors: strength: 1.0 keep_checkpoints: 5 max_steps: 5000000 - time_horizon: 1000 + time_horizon: 128 summary_freq: 10000 threaded: true Match3VisualObs: