arXiv Computer Vision
Player-1: Learning to Play from Synthetic Experience
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Aug 28
GameWAM: A World Action Model for Video Games
GameWAM is the first World-Action Model designed for native closed-loop gameplay and GUI control in modern video games. It jointly generates future visual observations and executable keyboard-mouse trajectories using parallel visual and action generative processes, block-causal conditioning, and flow matching. The model predicts gameplay/GUI mode at each step, handles heterogeneous native controls, and employs block-cycle control for long-horizon interaction, achieving competitive task success with fewer native actions than prior agents.
arXiv AI
Jul 3
WorldSample: Closed-loop Real-robot RL with World Modelling
arXiv:2607. 02431v1 Announce Type: cross Abstract: Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond the states observed in demonstrations.
arXiv Computer Vision
Sep 14
PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration
PAVXploreRL introduces a reinforcement learning framework that builds on a pretrained latent world model to explicitly optimize Physical Plausibility, Action Adherence, and Visual Fidelity (PAV) objectives. By combining in‑distribution expert trajectories with noise‑driven out‑of‑distribution action exploration, the method avoids reliance on paired video supervision and improves generalization. Experiments demonstrate a 5.6% average performance gain over pretrained baselines and more reliable policy evaluation with reduced overestimation bias.
arXiv AI
Aug 25
The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction
arXiv:2608.22301v1 Announce Type: cross Abstract: Humans imitate at the level of intent: given a demonstration, we infer its goal and carry it out with whatever tools, objects, and layouts are at han...
arXiv AI
Sep 30
Pixels to Keys: Exploring Spatial and Motion Cues in Gameplay Inverse Dynamics
arXiv:2609.37907v1 Announce Type: new Abstract: Video games offer scalable environments for studying perception and control in embodied agents.Abundant online gameplay videos could supply demonstrati...
arXiv Computer Vision
Oct 9
AgentGarten: Code Worlds for Evolving Agents
AgentGarten is a framework that links simulators and game engines with a shared neural renderer to create real‑time interactive virtual worlds. It uses a pretrained video model adapted to geometry conditions, refined with Adversarial Forcing, to produce realistic visual observations while maintaining consistent state and rules. The system enables agents to learn efficiently—achieving comparable performance in only four training rounds versus millions in traditional reinforcement learning—by distilling experience into playbooks that successive agents can inherit and improve upon.