Tag

#self-play

Every item tagged self-play, newest first.

5 items

Dota 2 with large scale deep reinforcement learning

OpenAI trained a Dota 2 bot using large-scale deep reinforcement learning, achieving a win rate of 60% against human players in 1v1 matches. The bot learned from self-play with 180,000 hours of experience, equivalent to 20 years of continuous play. This demonstrates the potential of deep learning for complex tasks. You can apply similar techniques to other challenging problems.

Key takeaways

60% win rate against human players in 1v1 Dota 2 matches.
Bot learned from 180,000 hours of self-play experience.
Deep reinforcement learning applied to a complex game.

OOpenAI#deep-reinforcement-learning #game-playing #self-play

researchJun 25

OpenAI Five

OpenAI developed OpenAI Five, a system of five neural networks that can defeat amateur human teams at Dota 2. The system learned to play through self-play, without human data or supervision. This achievement shows that AI can learn complex tasks through self-play alone. You can watch OpenAI Five play against humans on Twitch.

Key takeaways

OpenAI Five defeats amateur human teams at Dota 2.
Learned to play through 180,000 hours of self-play.
No human data or supervision required.

OOpenAI#ai-research #self-play #dota-2

researchOct 11

Competitive self-play

OpenAI researchers found that self-play enables simulated AIs to learn physical skills like tackling and catching without explicit design. Self-play adjusts difficulty to match AI skill level, facilitating improvement. This approach shows promise for developing more capable AI systems. You can apply self-play to train models in complex environments.

Key takeaways

Self-play enables AIs to learn physical skills without explicit design.
Self-play adjusts environment difficulty to AI skill level.
Self-play may be core to future powerful AI systems.

OOpenAI#self-play #ai-training #simulation

researchAug 16

More on Dota 2

OpenAI's Dota 2 AI system improved from barely matching a high-ranked player to beating top pros within a month through self-play. The system's performance leapfrogged human level to superhuman. This approach allows AI to generate its own training data, improving automatically as it gets better. You can apply similar self-play techniques to other complex tasks.

Key takeaways

Self-play improved Dota 2 AI from human-level to superhuman in 1 month.
Self-play generates training data automatically as the agent improves.
Techniques apply to complex tasks beyond Dota 2.

OOpenAI#self-play #deep-learning #ai-training

researchAug 11

Dota 2

OpenAI created a Dota 2 bot that beats top professionals in 1v1 matches under standard rules. The bot learned from self-play without imitation learning or tree search. This achievement demonstrates progress toward building AI systems that can accomplish goals in complex, human-involving situations. You can learn from OpenAI's approach to developing autonomous agents.

Key takeaways

Beats top professionals in 1v1 Dota 2 matches.
Learned from self-play, not imitation or tree search.
Advances development of AI in complex human situations.

OOpenAI#game-ai #autonomous-agents #self-play