%PDF-1.3 1 0 obj << /Kids [ 4 0 R 5 0 R 6 0 R 7 0 R 8 0 R 9 0 R 10 0 R 11 0 R 12 0 R ] /Type /Pages /Count 9 >> endobj 2 0 obj << /Subject (Neural Information Processing Systems http\072\057\057nips\056cc\057) /Publisher (Curran Associates\054 Inc\056) /Language (en\055US) /Created (2014) /EventType (Spotlight) /Description-Abstract (We describe how to use robust Markov decision processes for value function approximation with state aggregation\056 The robustness serves to reduce the sensitivity to the approximation error of sub\055optimal policies in comparison to classical methods such as fitted value iteration\056 This results in reducing the bounds on the gamma\055discounted infinite horizon performance loss by a factor of 1\057\0501\055gamma\051 while preserving polynomial\055time computational complexity\056 Our experimental results show that using the robust representation can significantly improve the solution quality with minimal additional computational cost\056) /Producer (PyPDF2) /Title (RAAM\072 The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning) /Date (2014) /ModDate (D\07220141202154922\05508\04700\047) /Published (2014) /Type (Conference Proceedings) /firstpage (1979) /Book (Advances in Neural Information Processing Systems 27) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (Z\056 Ghahramani and M\056 Welling and C\056 Cortes and N\056D\056 Lawrence and K\056Q\056 Weinberger) /Author (Marek Petrik\054 Dharmashankar Subramanian) /lastpage (1987) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 13 0 R /Parent 1 0 R /Type /Page /Resources 14 0 R /MediaBox [ 0 0 612 792 ] >> endobj 5 0 obj << /Contents 55 0 R /Parent 1 0 R /Type /Page /Resources 56 0 R /MediaBox [ 0 0 612 792 ] >> endobj 6 0 obj << /Contents 73 0 R /Parent 1 0 R /Type /Page /Resources 74 0 R /MediaBox [ 0 0 612 792 ] >> endobj 7 0 obj << /Contents 91 0 R /Parent 1 0 R /Type /Page /Resources 92 0 R /MediaBox [ 0 0 612 792 ] >> endobj 8 0 obj << /Contents 121 0 R /Parent 1 0 R /Type /Page /Resources 122 0 R /MediaBox [ 0 0 612 792 ] >> endobj 9 0 obj << /Contents 131 0 R /Parent 1 0 R /Type /Page /Resources 132 0 R /MediaBox [ 0 0 612 792 ] >> endobj 10 0 obj << /Contents 137 0 R /Parent 1 0 R /Type /Page /Resources 138 0 R /MediaBox [ 0 0 612 792 ] >> endobj 11 0 obj << /Contents 139 0 R /Parent 1 0 R /Resources 140 0 R /Group 194 0 R /MediaBox [ 0 0 612 792 ] /Type /Page >> endobj 12 0 obj << /Contents 196 0 R /Parent 1 0 R /Type /Page /Resources 197 0 R /MediaBox [ 0 0 612 792 ] >> endobj 13 0 obj << /Length 3215 /Filter /FlateDecode >> stream xZ[۶~_GiBd:ݤ=u;d