| Autor: |
Amin Babadi, Kourosh Naderi, Perttu Hämäläinen, Shaghayegh Roohi |
| Přispěvatelé: |
Professorship Hämäläinen Perttu, Department of Computer Science, Department of Media, Aalto-yliopisto, Aalto University |
| Rok vydání: |
2019 |
| Předmět: |
|
| Zdroj: |
CoG |
| Popis: |
This paper addresses the problem of synthesizing simulated humanoid climbing movements given the target holds, e.g., by the player of a climbing game. We contribute the first deep reinforcement learning solution that can handle interactive physically simulated humanoid climbing with more than one limb switching holds at the same time. A key component of our approach is Self-Supervised Episode State Initialization (SS- ESI), which ensures diverse exploration and speeds up learning, compared to a baseline approach where the climber is reset to an initial pose after failure. Our results also show that training with a multi-step action parameterization can produce both smoother movements and enable learning from slightly fewer explored actions at the cost of increased simulation time per action. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
