Dota 2
11 papers with code • 0 benchmarks • 0 datasets
Dota 2 is a multiplayer online battle arena (MOBA). The task is to train one-or-more agents to play and win the game.
( Image credit: OpenAI Five )
Benchmarks
These leaderboards are used to track progress in Dota 2
Latest papers
Semantic HELM: A Human-Readable Memory for Reinforcement Learning
Then we feed these tokens to a pretrained language model that serves the agent as memory and provides it with a coherent and human-readable representation of the past.
Beyond the Meta: Leveraging Game Design Parameters for Patch-Agnostic Esport Analytics
Therefore, the proposed methodology for representing characters can increase the life-spam of machine learning models as well as contribute to a higher performance when compared to traditional techniques typically employed within the literature.
Joint action loss for proximal policy optimization
ubiquition/drl
•
•
Instead, for each sub-action we calculate the loss separately, which is less prone to clipping during updates thereby making better use of samples.
Machine learning models for DOTA 2 outcomes prediction
Prediction of the real-time multiplayer online battle arena (MOBA) games' match outcome is one of the most important and exciting tasks in Esports analytical research.
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning
tencent-ailab/tleague_projpage
•
•
This poses non-trivial difficulties for researchers or engineers and prevents the application of MARL to a broader range of real-world problems.
Multi-Agent Collaboration via Reward Attribution Decomposition
In this work, we propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge and supports ad hoc team play.
Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game.
Time to Die: Death Prediction in Dota 2 using Deep Learning
adam-katona/dota2_death_prediction
•
•
Even though death events are rare within a game (1\% of the data), the model achieves 0. 377 precision with 0. 725 recall on test data when prompted to predict which of any of the 10 players of either team will die within 5 seconds.
An Empirical Model of Large-Batch Training
astooke/rlpyt
•
•
In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency.
Proximal Policy Optimization Algorithms
labmlai/annotated_deep_learning_paper_implementations
•
•
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.
