Enhancing Two-Player Performance Through Single-Player Knowledge Transfer: An Empirical Study on Atari 2600 Games
Not on the map. Why?
Abstract (arXiv)
Playing two-player games using reinforcement learning and self-play can be challenging due to the complexity of two-player environments and the possible instability in the training process. We propose that a reinforcement learning algorithm can train more efficiently and achieve improved performance in a two-player game if it leverages the knowledge from the single-player version of the same game. This study examines the proposed idea in ten different Atari 2600 environments using the Atari 2600 RAM as the input state. We discuss the advantages of using transfer learning from a single-player training process over training in a two-player setting from scratch, and demonstrate our results in a few measures such as training time and average total reward. We also discuss a method of calculating RAM complexity and its relationship to performance.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 22 Oct 2024.
Builds on
20 of 39 references.
References · 20
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2016Progressive Neural Networkscited by 1,332
- 2019A Comprehensive Survey on Transfer Learningcited by 1,154
- 2019Improving Sample Efficiency in Model-Free Reinforcement Learning from Imagescited by 268
- 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 209
- 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 180
- 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 176
- 2021Tianshou: a Highly Modularized Deep Reinforcement Learning Librarycited by 139
- 2019A Survey of Deep Reinforcement Learning in Video Gamescited by 73
- 2018Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translationcited by 50
- 2023Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manualscited by 45
- 2020Finding Effective Security Strategies through Reinforcement Learning and Self-Playcited by 32
8 more
- 2017Deep Learning for Video Game Playingcited by 30
- 2020SuperSuit: Simple Microwrappers for Reinforcement Learning Environmentscited by 10
- 2021Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Modelcited by 9
- 2021Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learningcited by 7
- 2022Transformer-based Value Function Decomposition for Cooperative Multi-agent Reinforcement Learning in StarCraftcited by 5
- 2019Marathon Environments: Multi-Agent Continuous Control Benchmarks in a Modern Video Game Enginecited by 2
- 2022On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfercited by 2
- 2022Task Relabelling for Multi-task Transfer using Successor Featurescited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.