RTA trains a VLM as a progress ordinal scorer via GRPO on shuffled expert frames and uses Spearman rank correlation with temporal indices as a bounded RL reward, matching or exceeding prior video reward methods on discrete and continuous control benchmarks.
Enhancing vision- language model training with reinforcement learning in synthetic worlds for real-world success
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3representative citing papers
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.
RoboAgent chains basic vision-language capabilities inside a single VLM via a scheduler and trains it in three stages (behavior cloning, DAgger, RL) to improve embodied task planning.
citing papers explorer
-
Rank-Then-Act: Reward-Free Control from Frame-Order Progress
RTA trains a VLM as a progress ordinal scorer via GRPO on shuffled expert frames and uses Spearman rank correlation with temporal indices as a bounded RL reward, matching or exceeding prior video reward methods on discrete and continuous control benchmarks.
-
Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.
-
RoboAgent: Chaining Basic Capabilities for Embodied Task Planning
RoboAgent chains basic vision-language capabilities inside a single VLM via a scheduler and trains it in three stages (behavior cloning, DAgger, RL) to improve embodied task planning.