21. S Sample-efficient multitask deep RL, on real robots, directly from pixels! The key is to enable agent... Sample-efficient multitask deep RL, on real robots, directly from pixels! The key is to enable agents to set their own goals and autonomously practice reaching them. Read more on t 09/07 04:30 ♡
22. S Should you plan ahead or learn by trial and error? Read @Vitchyr's BAIR blog post to see how tempora... Should you plan ahead or learn by trial and error? Read @Vitchyr 's BAIR blog post to see how temporal difference models (TDMs) combine the advantages of model-based and model- 04/27 07:41 ♡