Scalable Agent is the open implementation of IMPALA (Importance Weighted Actor-Learner Architectures), a highly scalable distributed reinforcement learning framework developed by Google DeepMind. IMPALA introduced a new paradigm for efficiently training agents across large-scale environments by decoupling acting and learning processes. In this architecture, multiple actor processes interact with their environments in parallel to collect trajectories, which are then asynchronously sent to a centralized learner for policy updates. The learner uses importance weighting to correct for policy lag between actors and the learner, enabling stable off-policy training at scale. ...