Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards
–Neural Information Processing Systems
When the index of the agent's last visited state embedding in the demonstration
Neural Information Processing Systems
Nov-13-2025, 16:06:44 GMT
- Country:
- North America > Canada (0.04)
- Genre:
- Workflow (0.69)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (1.00)
- Robots (0.69)
- Information Technology > Artificial Intelligence