RL Unplugged: A Suite of Benchmarks for Ofﬂine Reinforcement Learning

How researchers see this paper

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

Critic Regularized Regression (2020, methodology): “We experiment with the continuous control tasks introduced in RL Unplugged (RLU) [3].”
Acme: A Research Framework for Distributed Reinforcement Learning (2020, methodology): “Promising recent attempts at overcoming exploration in such tasks leverage demonstrations of successful trajectories (Kim et al., 2013; Hester et al., 2017; Vecerik et al., 2017; Nair et al., 2018; Gulcehre et al., 2020), dubbed the RL with Expert Demonstrations (RLED; Piot et al., 2014).”
A Generalist Agent (2022, methodology): “Moreover, this choice has been adopted by off-line RL benchmarks (Gulcehre et al., 2020; Fu et al., 2020) and recent works on large sequence neural networks for control, including decision transformers (Chen et al., 2021b; Reid et al., 2022; Zheng et al., 2022) and the Trajectory Transformer of…”
Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism (2021, background): “Conservatism in Offline RL In practice, such high coverage assumptions on batch dataset also known as data diversity [7] often fail to hold [5], [43], [70].”
A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems (2022, methodology): “[35], to provide a meaningful This article has been accepted for inclusion in a future issue of this journal.”