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).

An Introduction to Deep Reinforcement Learning

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.

PMCTS: Principled Parallelized Inference Time Scaling with Particle Monte Carlo Tree Search

The paper introduces Particle MCTS (PMCTS), a parallelized version of Monte Carlo Tree Search designed for GPU acceleration and batch-parallel neural network evaluations. PMCTS preserves policy improvement guarantees of modern MCTS algorithms while scaling efficiently with parallel compute. Empirical results show that PMCTS consistently outperforms or matches heuristic-based baselines across various MCTS and reinforcement learning domains, including chess, Go, and both discrete and continuous control benchmarks.

Streaming Deep Reinforcement Learning Finally Works

arXiv:2410.14606v3 Announce Type: replace Abstract: Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streami...