An Introduction to Deep Reinforcement Learning

Dota 2 with large scale deep reinforcement learning

Stochastic Neural Networks for hierarchical reinforcement learning

An Introduction to Q-Learning Part 1

Introducing ⚔️ AI vs. AI ⚔️ a deep reinforcement learning multi-agents competition system

Learning to Play: Reinforcement Learning and Games

arXiv:2610.17391v1 Announce Type: new Abstract: Amazing breakthroughs in reinforcement learning have taken place. Computers teach themselves to play Chess and Go and beat world champions. There is ta...

An Introduction to Q-Learning Part 2/2

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.

Quantifying generalization in reinforcement learning

We’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to transfer its experience to novel situations and has already helped clarify a longstanding puzzle in reinforcement learning. CoinRun strikes a desirable balance in complexity: the environment is simpler than traditional platformer games like Sonic the Hedgehog but still poses a worthy generalization challenge for state of the art algorithms.

Integrating Physics-Informed Neural Networks for Safe Reinforcement Learning in a 1-DoF Helicopter System

arXiv:2607. 03125v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) offers powerful control for industrial cyber-physical systems (ICPSs), but its "black-box" exploration risks violating strict hardware safety limits.

Benchmarking safe exploration in deep reinforcement learning

RL²: Fast reinforcement learning via slow reinforcement learning

Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks

arXiv:2605. 22305v2 Announce Type: replace Abstract: We analytically solve the Mountain Car problem, a canonical benchmark in RL, and derive an optimal control solution, closing a gap after 36 years.