Скачать или смотреть Unity ML Agents PushBlock Execution After Training

Single brain agent in action at runtime after training using Unity ML Agents and the PushBlock example environment made by Unity. The full training session lasted almost 6 minutes (about 20,000 steps) across 32 platforms like the one shown in the video.
Watch the training video here:    • Unity ML Agents - PushBlock Training Session  .

Description from the Unity Examples page:
Set-up: A platforming environment where the agent can push a block around.
Goal: The agent must push the block to the goal.
Agents: The environment contains one agent linked to a single brain.
Agent Reward Function:
-0.0025 for every step.
+1.0 if the block touches the goal.
Brains: One brain with the following observation/action space.
Vector Observation space: (Continuous) 15 variables corresponding to position and velocities of agent, block, and goal.
Vector Action space: (Continuous) Size of 2, corresponding to movement in X and Z directions.

Unity ML Agents: https://github.com/Unity-Technologies...