Reinforcement Learning Benchmarks and Bake-offs II A workshop at the 2005 NIPS conference

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Benchmarks for Deep Off-Policy Evaluation (2021, background): “Outside of OPE, standardized benchmark suites have led to considerable standardization and progress in RL (Stone & Sutton, 2001; Dutech et al., 2005; Riedmiller et al., 2007).”
Model-based function approximation in reinforcement learning (2007, methodology): “This section compares the performance of AMBI to algorithms submitted to the RL benchmarking workshop held at NIPS 2005 [4].”
Empirical evaluation methods for multiobjective reinforcement learning algorithms (2011, methodology): “This process has been aided by the RL bake-offs which have been held in conjunction with major conferences in recent years (see for example Dutech et al. 2005).”
Safe Policy Iteration (2013, methodology): “In this work, we consider the simplified version of the blackjack game usually used as RL benchmark (refer to (Dutech et al., 2005) for more details).”
Acceleration of Reinforcement Learning by Policy Evaluation Using Nonstationary Iterative Method (2014, background): “2) Inverted Pendulum Problem: This section considers an inverted pendulum problem, which is made referring problems in reference [13].”