The Arcade Learning Environment: An Evaluation Platform for General Agents (Extended Abstract)
By Marc G. Bellemare, Yavar Naddaf, Joel Veness, Michael H. Bowling. 2015
46 citations recorded by the source corpus.
Subfields: Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Reinforcement Learning
- Sergey Levine
- Pieter Abbeel
- Marc G. Bellemare
- David Silver
- Yuxi Li
- Chelsea Finn
- Ofir Nachum
- Hado van Hasselt
Citations in the corpus
- Measuring Massive Multitask Language Understanding (2020, background): “There are 57 tasks in total, which is also the number of Atari games (Bellemare et al., 2013), all of which are listed in Appendix B.”
- Model-Based Reinforcement Learning for Atari (2019, methodology): “Atari games gained prominence as a benchmark for reinforcement learning with the introduction of the Arcade Learning Environment (ALE) Bellemare et al. (2015).”
- Rainbow: Combining Improvements in Deep Reinforcement Learning (2017, methodology): “In fact, their combination results in new state-of-the-art results on the benchmark suite of 57 Atari 2600 games from the Arcade Learning Environment (Bellemare et al. 2013), both in terms of data efficiency and of final performance.”
- Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents (2017, methodology): “Bellemare et al. (2015) and Braylan, Hollenbeck, Meyerson, and Miikkulainen (2015) showed that this determinism can be exploited by agents that simply memorize an effective sequence of actions, attaining state-of-the-art scores while ignoring the agent’s perceived state altogether.”
- Recent advances in reinforcement learning in finance (2021, methodology): “” Both these ideas dramatically improve the empirical performance of the algorithm and DQN has been shown to have a strong performance for a variety of ATARI games (Bellemare et al., 2013).”
- Representation Learning via Invariant Causal Mechanisms (2020, unknown): “Specifically, we test RELIC on the suite of Atari games (Bellemare et al., 2013) which consists of 57 diverse games of varying difficulty.”