Dota 2 with large scale deep reinforcement learning

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

arXiv:2607. 07769v1 Announce Type: cross Abstract: Starting from the utilization of deep neural networks to approximate the state-action value function that led to winning one of the most challenging games, to algorithmic advancements that allowed solving problems without even explicitly stating the rules of the challenge at hand, reinforcement learning research has been the center of remarkable scientific progress for the past decade.

RL²: Fast reinforcement learning via slow reinforcement learning

More on Dota 2

Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute. In the span of a month, our system went from barely matching a high-ranked player to beating the top pros and has continued to improve since then.

Reinforcement Learning from Denoising Feedback

arXiv:2605. 25638v2 Announce Type: replace-cross Abstract: Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (DLMs).

Hierarchical Reinforcement Learning with Optimal Level Synchronization Based on Flow-Based Deep Generative Model

arXiv:2107. 08183v2 Announce Type: replace Abstract: High-dimensional state and action spaces combined with sparse reward structures in reinforcement learning (RL) environments typically require advanced control architectures.

V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control

arXiv:2608. 07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collection is costly.

Dota 2

We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the game from scratch by self-play, and does not use imitation learning or tree search.

LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent

arXiv:2604. 17931v3 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents.

Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns

arXiv:2503. 03660v4 Announce Type: replace Abstract: We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets.

Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning

arXiv:2606. 20411v1 Announce Type: new Abstract: Direct Advantage Estimation (DAE) has been shown to improve the sample efficiency of deep reinforcement learning algorithms.

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, making it unclear which components are essential for scalability.

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

arXiv:2606. 05555v1 Announce Type: new Abstract: Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge.