Inference-time dynamic planning budgets for TD-MPC2 with paired return and latency evaluation.
-
Updated
Aug 9, 2026 - Python
#
td-mpc2
Here are 2 public repositories matching this topic...
Reinforcement learning (PPO, TD-MPC2) and behavior cloning for closed-loop harvest control of a simulated Spirulina photobioreactor, with a curriculum-gated training pipeline and held-out validation.
reinforcement-learning agent-based-modeling behavioral-cloning photobioreactor spirulina gymnasium curriculum-learning ppo reinforcement-learning-environments stable-baselines3 bioprocess-modelling td-mpc2
-
Updated
Aug 26, 2026 - Python
Add this topic to your repo
To associate your repository with the td-mpc2 topic, visit your repo's landing page and select "manage topics."