Tag: reward-modeling

Sep 27, 2026

• rl-robotics
• vla
• online-rl
• reward-modeling
• vla-posttraining

Sep 15, 2026

• vla-posttraining
• reward-modeling
• self-improvement
• autonomous-evaluation

Jul 22, 2026

• rl-robotics
• reward-modeling
• survey

Jul 14, 2026

• rl-robotics
• reward-modeling
• synthetic-data
• vla-posttraining

Jul 06, 2026

• reward-modeling
• value-learning
• imitation-learning
• mistake-recovery

Jun 30, 2026

• preference-learning
• reward-modeling
• long-horizon-manipulation
• human-feedback
• vla-posttraining

Jun 29, 2026

• rl-robotics
• preference-learning
• reward-modeling
• locomotion
• vla-posttraining

Jun 26, 2026

• reward-modeling
• process-rewards
• sparse-reward
• rl-finetuning

Jun 24, 2026

• rl-robotics
• reward-modeling
• single-demonstration

Jun 09, 2026

• reward-modeling
• stage-aware
• mixture-of-experts
• self-improvement
• SPIRAL
• long-horizon
• on-robot-RL
• VLA

Jun 08, 2026

• rl
• vla
• reward-modeling
• failure-recovery
• sim-to-real
• vla-posttraining

Jun 04, 2026

• vla
• world-models
• position-paper
• data-interfaces
• embodiment-gap
• reward-modeling
• survey

Jun 01, 2026

• reinforcement-learning
• reward-modeling
• test-time-adaptation
• vla-posttraining