Classical Planning with Simulators: Results on the Atari Video Games

By Nir Lipovetzky, Miquel Ramírez, Hector Geffner. 2015

89 citations recorded by the source corpus.

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

Citations in the corpus

Go-Explore: a New Approach for Hard-Exploration Problems (2019, neutral): “The location of the agent could be extracted by training a simple classifier, or in an unsupervised way through contingency-awareness [39], but it turns out that, in both Montezuma’s Revenge and Pitfall, some pixel values only occur in the character sprite, making it trivial to identify the characte”
Learning to Prune Dominated Action Sequences in Online Black-Box Planning (2016, methodology): “As with previous work (Bellemare et al. 2013; Lipovetzky, Ramirez, and Geffner 2015), all algorithms cache simulation results, so simulations are not executed for cached states, and cached states do not count against the simulation frame budget.”
The Benchmark Lottery (2021, background): “While in some publications episodes terminate when the game is over [Bellemare et al., 2013, Hausknecht et al., 2014, Liang et al., 2015, Lipovetzky et al., 2015, Martin et al., 2017], while others papers choose to terminate the training episodes for a subset of the games when the agent loses a…”
State of the Art Control of Atari Games Using Shallow Reinforcement Learning (2015, methodology): “These feature sets were, for some time, the standard representations for Atari 2600 games, being directly used in other work [7, 16, 17] or serving as the base for more elaborate feature sets [4].”
Model-free, Model-based, and General Intelligence (2018, methodology): “In particular, IW(1) has been used effectively as an on-line planner in the Atari video games in two modes: with the memory states of the emulator [Lipovetzky et al., 2015] and with the screen states [Bandres et al.”
Selecting Subgoals using Deep Learning in Minecraft : A Preliminary Report (2016, background): “Deep Learning has recently been brought into the domain of video games including Atari [Mnih et al., 2015] [Lipovetsky et al., 2015].”
Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games (2016, background): “There are a number of approaches to building ATARI game players, including some that do not use DL (e.g., Bellemare et al. 2012a, 2012b, 2013a, Lipovetzky et al. 2015).”