Can Deep Reinforcement Learning Solve Erdos-selfridge-spencer Games?

Abstract

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,

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyraghu2017can

Related papers

• Deep RTS: A Game Environment For Deep Reinforcement Learning In Real-time Strategy Games (2018)16.97
• Learning To Design Games: Strategic Environments In Reinforcement Learning (2017)0.00
• Deep Reinforcement Learning From Self-play In Imperfect-information Games (2016)0.00
• Explore Reinforced: Equilibrium Approximation With Reinforcement Learning (2024)0.00
• Stackelberg Games For Learning Emergent Behaviors During Competitive Autocurricula (2023)5.84
• Generalization And Regularization In DQN (2018)0.00
• Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey (2021)0.00
• Ecological Reinforcement Learning (2020)8.35