Timezone: »

 
Poster
Control What You Can: Intrinsically Motivated Task-Planning Agent
Sebastian Blaes · Marin Vlastelica Pogančić · Jiajie Zhu · Georg Martius

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #213
in Reinforcement Learning and Planning -- Planning »

We present a novel intrinsically motivated agent that learns how to control the environment in a sample efficient manner, that is with as few environment interactions as possible, by optimizing learning progress. It learns what can be controlled, how to allocate time and attention as well as the relations between objects using surprise-based motivation. The effectiveness of our method is demonstrated in a synthetic and robotic manipulation environment yielding considerably improved performance and smaller sample complexity compared to an intrinsically motivated, non-hierarchical and state-of-the-art hierarchical baseline. In a nutshell, our work combines several task-level planning agent structures (backtracking search on task-graph, probabilistic road-maps, allocation of search efforts) with intrinsic motivation to achieve learning from scratch.

Keywords: Planning · Reinforcement Learning and Planning · Reinforcement Learning and Planning -> Exploration; Reinforcement Learning and Planning · Hierarchical RL; Reinforcement Learn

Author Information

Sebastian Blaes (Max-Planck Institute for Intelligent Systems, Tuebingen, Germany)
Marin Vlastelica Pogančić (Max Planck Institute for Intelligent Systems)
Jiajie Zhu (Max Planck Institute for Intelligent Systems)
Georg Martius (MPI for Intelligent Systems)

More from the Same Authors