Self-Paced Deep Reinforcement Learning
–Neural Information Processing Systems
In contrast, we propose to generate the curriculum based on a principled inference view on RL. Our approach generates the curriculum based on two quantities: The value function of the agent and the KL divergence to a target distribution of tasks.
Neural Information Processing Systems
Nov-14-2025, 04:32:26 GMT
- Country:
- Europe
- Finland > Pirkanmaa
- Tampere (0.04)
- Germany > Hesse
- Darmstadt Region > Darmstadt (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Finland > Pirkanmaa
- North America > Canada (0.04)
- Europe
- Industry:
- Leisure & Entertainment (0.46)
- Technology: