Timezone: »

Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Maithra Raghu · Alexander Irpan · Jacob Andreas · Bobby Kleinberg · Quoc Le · Jon Kleinberg

Thu Jul 12 09:15 AM -- 12:00 PM (PDT) @ Hall B #29

Deep reinforcement learning has achieved many recent successes, but our understanding of its strengths and limitations is hampered by the lack of rich environments in which we can fully characterize optimal behavior, and correspondingly diagnose individual actions against such a characterization. Here we consider a family of combinatorial games, arising from work of Erdos, Selfridge, and Spencer, and we propose their use as environments for evaluating and comparing different approaches to reinforcement learning. These games have a number of appealing features: they are challenging for current learning approaches, but they form (i) a low-dimensional, simply parametrized environment where (ii) there is a linear closed form solution for optimal behavior from any state, and (iii) the difficulty of the game can be tuned by changing environment parameters in an interpretable way. We use these Erdos-Selfridge-Spencer games not only to compare different algorithms, but test for generalization, make comparisons to supervised learning, analyse multiagent play, and even develop a self play algorithm.

Author Information

Maithra Raghu (Google Brain / Cornell University)
Alexander Irpan (Google)
Jacob Andreas (UC Berkeley)
Bobby Kleinberg (Cornell)
Quoc Le (Google Brain)
Jon Kleinberg (Cornell University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors