Petar Kormushev

3 papers · 2018–2021 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) 🧭 Keyword Pioneer

Venues

AAAI (1) ICLR (1) ICML (1)

Top co-authors

Vitaly Levdik (2) Arash Tavakoli (2) Fabio Pardo (2) Mehdi Fatemi (1)

Research topics

Reinforcement Learning (3) Applications (3) Methods (3) Deep Learning (2) Machine Learning (2) Architectures (2) Learning Types · Machine Learning (2) Core Methods (1) Learning Types · Deep Learning (1)

Keywords

reinforcement learning (2) policy optimization (1) markov decision process (1) hypergraphs (1) value iteration (1) off-policy learning (1) convolutional neural network (1) goal-conditioned policy (1) exploration strategy (1) goal-conditioned reinforcement learning (1) markov property (1) control task (1) experience replay (1) time limit (1) episodic training (1) combinatorial structure (1) all-goals update (1) all-goals updating (1) q-networks (1) action vertices (1)

Papers

Learning to Represent Action Values as a Hypergraph on the Action Vertices ICLR 2021 Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks AAAI 2020 Time Limits in Reinforcement Learning ICML 2018