Timezone: »

Model-Based Episodic Memory Induces Dynamic Hybrid Controls
Hung Le · Thommen Karimpanal George · Majid Abdolshah · Truyen Tran · Svetha Venkatesh

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @ None #None

Episodic control enables sample efficiency in reinforcement learning by recalling past experiences from an episodic memory. We propose a new model-based episodic memory of trajectories addressing current limitations of episodic control. Our memory estimates trajectory values, guiding the agent towards good policies. Built upon the memory, we construct a complementary learning model via a dynamic hybrid control unifying model-based, episodic and habitual learning into a single architecture. Experiments demonstrate that our model allows significantly faster and better learning than other strong reinforcement learning agents across a variety of environments including stochastic and non-Markovian settings.

Author Information

Hung Le (Deakin University)
Thommen Karimpanal George (Deakin University)
Majid Abdolshah (Deakin University)
Truyen Tran (Deakin University)
Svetha Venkatesh (Deakin University)

More from the Same Authors