https://plancherb1.github.io/tags/replay-buffer/ Recent content in Replay Buffer on Brian Plancher Hugo -- gohugo.io en-us © {year} Brian Plancher Wed, 24 Jun 2026 00:00:03 +0000 https://plancherb1.github.io/publication/mpcinjection/ Wed, 24 Jun 2026 00:00:03 +0000 https://plancherb1.github.io/publication/mpcinjection/ We present MPC-Injection, a low-overhead method that steers RL toward a designer-preferred gait by inserting transitions into the replay buffer from a model predictive controller solving the same Markov decision process. Unlike reward shaping, MPC-Injection does not require redesigning the task reward, and unlike adversarial imitation learning, it adds no discriminator, no kinematic retargeting, and no auxiliary objective. Instead, the controller’s preferred behavior is transferred to the policy purely through the replay state distribution.