Research map / Learning theory and algorithms / Submodular and game algorithms
An Efficient Deep Reinforcement Learning Algorithm for Solving Imperfect Information Extensive-Form Games
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Deep FTRL-ORW instead of the compared model-free methods | Kuhn Poker, Leduc Poker, and Goofspiel(5) · Kuhn Poker, Leduc Poker, Goofspiel(5) | exploitability | Helped |
| Use Deep FTRL-ORW instead of NFSP | Kuhn Poker, Leduc Poker, and Goofspiel(5) · Kuhn Poker, Leduc Poker, Goofspiel(5) | episodes to achieve similar exploitability: around 40-50% | Helped |
| Use Deep FTRL-ORW instead of NFSP | Phantom Tic Tac Toe and Dark Hex · Phantom Tic Tac Toe, Dark Hex(4), Dark Hex(5) | reward against random agent | Helped |
| Use Deep FTRL-ORW instead of OS-MCCFR | Kuhn Poker, Leduc Poker, and Goofspiel(5) · Kuhn Poker, Leduc Poker, Goofspiel(5) | exploitability | Mixed |
| Use OS-Deep CFR instead of OS-MCCFR | Kuhn Poker, Leduc Poker, and Goofspiel(5) · Kuhn Poker, Leduc Poker, Goofspiel(5) | exploitability | Hurt |
Closest papers by meaning
- Double Neural Counterfactual Regret Minimization (ICLR 2020 · similarity 0.92)
- Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game (ICLR 2022 · similarity 0.91)
- Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games (AAAI 2021 · similarity 0.90)
- The Power of Regularization in Solving Extensive-Form Games (ICLR 2023 · similarity 0.89)
- Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback (ICML 2025 · similarity 0.88)
- RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning (ICML 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.