Skip to search formSkip to main contentSkip to account menu

SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving

The design goals of SMARTS (Scalable Multi-Agent RL Training School) are described, its basic architecture and its key features are explained, and its use is illustrated through concrete multi-agent experiments on interactive scenarios.
View PDF on arXiv (opens in a new tab)

Multi-Agent Reinforcement Learning for Order-dispatching via Order-Vehicle Distribution Matching

Experiments show that the proposed decentralized execution order-dispatching method outperforms the baselines in terms of accumulated driver income (ADI) and Order Response Rate (ORR) in various traffic environments.
View on ACM (opens in a new tab)

SMARTS: An Open-Source Scalable Multi-Agent RL Training School for Autonomous Driving

View Paper (opens in a new tab)

Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts

A novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy Optimization (AORPO), is proposed, which can achieve improved sample efficiency with comparable asymptotic performance over the compared MARL methods.
View PDF on arXiv (opens in a new tab)

Generative adversarial exploration for reinforcement learning

This work proposes a novel method called GAEX to encourage exploration in RL via introducing an intrinsic reward output from a generative adversarial network, where the generator provides fake samples of states that help discriminator identify those less frequently visited states.
View on ACM (opens in a new tab)

CoRide

View via Publisher (opens in a new tab)

Multi-Agent Interactions Modeling with Correlated Policies

A Decentralized Adversarial Imitation Learning algorithm with Correlated policies (CoDAIL), which allows for decentralized training and execution and outperforms state-of-the-art multi-agent imitation learning methods.
View PDF on arXiv (opens in a new tab)

MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning

MALib is a scalable and efficient computing framework for population-based multi-agent reinforcement learning that enables efficient code reuse and flexible deployments on different distributed computing paradigms and achieves throughput higher than 40K FPS on a single machine with 32 CPU cores.
View PDF on arXiv (opens in a new tab)

Regioned Episodic Reinforcement Learning

Regioned Episodic Reinforcement Learning (RERL) is introduced that combines the episodic and goal-oriented learning strengths and leads to a more sample efficient andective algorithm.

Efficient Policy Space Response Oracles

Theoretically, the solution procedures of EPSRO offer a monotonic improvement on the exploitability, which none of existing PSRO methods possess, and it is proved that the no-regret optimization has a regret bound of O (cid:112) T log [( k 2 + k ) / 2]) , where k is the size of restricted policy set.
View PDF on arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)