Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use AnnaMats/ppo-Pyramids-Training with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use AnnaMats/ppo-Pyramids-Training with ml-agents:
mlagents-load-from-hf --repo-id="AnnaMats/ppo-Pyramids-Training" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
| using UnityEngine; | |
| using Unity.MLAgents; | |
| using Unity.MLAgents.Actuators; | |
| using Unity.MLAgents.Sensors.Reflection; | |
| public class Ball3DHardAgent : Agent | |
| { | |
| [] | |
| public GameObject ball; | |
| Rigidbody m_BallRb; | |
| EnvironmentParameters m_ResetParams; | |
| public override void Initialize() | |
| { | |
| m_BallRb = ball.GetComponent<Rigidbody>(); | |
| m_ResetParams = Academy.Instance.EnvironmentParameters; | |
| SetResetParameters(); | |
| } | |
| [] | |
| Vector2 Rotation | |
| { | |
| get | |
| { | |
| return new Vector2(gameObject.transform.rotation.z, gameObject.transform.rotation.x); | |
| } | |
| } | |
| [] | |
| Vector3 PositionDelta | |
| { | |
| get | |
| { | |
| return ball.transform.position - gameObject.transform.position; | |
| } | |
| } | |
| public override void OnActionReceived(ActionBuffers actionBuffers) | |
| { | |
| var continuousActions = actionBuffers.ContinuousActions; | |
| var actionZ = 2f * Mathf.Clamp(continuousActions[0], -1f, 1f); | |
| var actionX = 2f * Mathf.Clamp(continuousActions[1], -1f, 1f); | |
| if ((gameObject.transform.rotation.z < 0.25f && actionZ > 0f) || | |
| (gameObject.transform.rotation.z > -0.25f && actionZ < 0f)) | |
| { | |
| gameObject.transform.Rotate(new Vector3(0, 0, 1), actionZ); | |
| } | |
| if ((gameObject.transform.rotation.x < 0.25f && actionX > 0f) || | |
| (gameObject.transform.rotation.x > -0.25f && actionX < 0f)) | |
| { | |
| gameObject.transform.Rotate(new Vector3(1, 0, 0), actionX); | |
| } | |
| if ((ball.transform.position.y - gameObject.transform.position.y) < -2f || | |
| Mathf.Abs(ball.transform.position.x - gameObject.transform.position.x) > 3f || | |
| Mathf.Abs(ball.transform.position.z - gameObject.transform.position.z) > 3f) | |
| { | |
| SetReward(-1f); | |
| EndEpisode(); | |
| } | |
| else | |
| { | |
| SetReward(0.1f); | |
| } | |
| } | |
| public override void OnEpisodeBegin() | |
| { | |
| gameObject.transform.rotation = new Quaternion(0f, 0f, 0f, 0f); | |
| gameObject.transform.Rotate(new Vector3(1, 0, 0), Random.Range(-10f, 10f)); | |
| gameObject.transform.Rotate(new Vector3(0, 0, 1), Random.Range(-10f, 10f)); | |
| m_BallRb.velocity = new Vector3(0f, 0f, 0f); | |
| ball.transform.position = new Vector3(Random.Range(-1.5f, 1.5f), 4f, Random.Range(-1.5f, 1.5f)) | |
| + gameObject.transform.position; | |
| } | |
| public void SetBall() | |
| { | |
| //Set the attributes of the ball by fetching the information from the academy | |
| m_BallRb.mass = m_ResetParams.GetWithDefault("mass", 1.0f); | |
| var scale = m_ResetParams.GetWithDefault("scale", 1.0f); | |
| ball.transform.localScale = new Vector3(scale, scale, scale); | |
| } | |
| public void SetResetParameters() | |
| { | |
| SetBall(); | |
| } | |
| } | |