Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach

Documenti analoghi

• Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards
  di: Kwon, Hyeokjin, et al.
  Pubblicazione: (2024)
• RVN-Bench: A Benchmark for Reactive Visual Navigation
  di: Lee, Jaewon, et al.
  Pubblicazione: (2026)
• Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning
  di: Kim, Dohyeong, et al.
  Pubblicazione: (2024)
• Semantic Environment Atlas for Object-Goal Navigation
  di: Kim, Nuri, et al.
  Pubblicazione: (2024)
• Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
  di: Kim, Junseok, et al.
  Pubblicazione: (2026)