EMI: Exploration with Mutual Information

By Hyoungseok Kim, Jaekyeom Kim, Yeonwoo Jeong, Sergey Levine, Hyun Oh Song. 2018

107 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.

Citations in the corpus

RODE: Learning Roles to Decompose Multi-Agent Tasks (2020, background): “, 2019) actions in RL, learn linear dynamics that help exploration (Kim et al., 2019), and transfer policy across different tasks (Chen et al.”
Know Your Action Set: Learning Action Relations for Reinforcement Learning (2022, background): “, 2019b), and efficient exploration by exploiting the shared structure among actions (He et al., 2015; Tennenholtz & Mannor, 2019; Kim et al., 2019).”
Never Give Up: Learning Directed Exploration Strategies (2020, background): “Recent works have explored ways of measuring novelty by learning controllable aspects of an environment (Kim et al., 2018; Warde-Farley et al., 2018), and we believe that some of these ideas could be also useful in this setting.”
Wasserstein Dependency Measure for Representation Learning (2019, background): “…and image understanding (van den Oord et al., 2018; Hjelm et al., 2018), reinforcement learning (Jaderberg et al., 2016; Dwibedi et al., 2018; Kim et al., 2018), imitation learning (Sermanet et al., 2017; Aytar et al., 2018), and natural language processing (Devlin et al., 2018; Radford et…”
Provable Rich Observation Reinforcement Learning with Combinatorial Latent States (2021, methodology): “Finally, we comment that the contrastive learning technique used in this paper has been used by other reinforcement learning algorithms for learning feature representation (e.g., Kim et al. (2019); Nachum et al. (2019); Srinivas et al. (2020)) without theoretical guarantee.”
Generalization to New Actions in Reinforcement Learning (2020, background): “…of discrete actions have been primarily used to ease learning in large discrete action spaces (Dulac-Arnold et al., 2015; Chandak et al., 2019) or exploiting the shared structure among actions for efficient learning and exploration (He et al., 2015; Tennenholtz & Mannor, 2019; Kim et al., 2019).”
Exploration in Deep Reinforcement Learning: A Survey (2022, methodology): “[46] TRPO Prediction error Atari: Frostbite 6000 (ICM 3000) Atari Images Ac MB D/ D”
BeBold: Exploration Beyond the Boundary of Explored Regions (2020, background): “DynamicAE (Stadie et al., 2015) computes the distance between the predicted and the real state on the output of an autoencoder, ICM (Pathak et al., 2017) learns the state representation through a forward and inverse model and EMI (Kim et al., 2018) computes the representation through maximizng mutua”
Dynamics-aware Embeddings (2019, background): “Other work has proposed to use mutual information maximization to learn embeddings which facilitate exploration via intrinsic motivation (Kim et al., 2018).”