Automata-conditioned reinforcement learning (RL) has given promising results for learning multi-task policies capable of performing temporally extended objectives given at runtime, done by pretraining and freezing automata embeddings prior to training the downstream policy. However, no theoretical guarantees were given. This work provides a theoretical framework for the automata-conditioned RL problem and shows that it is probably approximately correct learnable. We then present a technique for learning provably correct automata embeddings, guaranteeing optimal multi-task policy learning. Our experimental evaluation confirms these theoretical results.
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Sony AI（索尼人工智能研究院）
Goal-conditioned reinforcement learning (GCRL) has a wide range of potential real-world applications, including manipulation and navigation problems in robotics. Especially in such robotics tasks, sample efficiency is of the utmost importance for GCRL since, by default, the agent is only rewarded when it reaches its goal. While several methods have been proposed to improve the sample efficiency of GCRL, one relatively under-studied approach is the design of neural architectures to support sample efficiency. In this work, we introduce a novel neural architecture for GCRL that achieves significa…
This paper investigates methods for estimating the optimal stochastic control policy for a Markov Decision Process with unknown transition dynamics and an unknown reward function. This form of model-free reinforcement learning comprises many real world systems such as playing video games, simulated control tasks, and real robot locomotion. Existing methods for estimating the optimal stochastic control policy rely on high variance estimates of the policy descent. However, these methods are not guaranteed to find the optimal stochastic policy, and the high variance gradient estimates make conver…
Many real-world scenarios involve teams of agents that have to coordinate their actions to reach a shared goal. We focus on the setting in which a team of agents faces an opponent in a zero-sum, imperfect-information game. Team members can coordinate their strategies before the beginning of the game, but are unable to communicate during the playing phase of the game. This is the case, for example, in Bridge, collusion in poker, and collusion in bidding. In this setting, model-free RL methods are oftentimes unable to capture coordination because agents' policies are executed in a decentralized …
The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning
Inria Centre at the University of Bordeaux（波尔多大学Inria中心）；Allen Discovery Center at Tufts University（塔夫茨大学艾伦发现中心）；Wyss Institute for Biologically Inspired Engineering at Harvard University（哈佛大学Wyss生物启发工程研究所）；Inria（法国国家信息与自动化研究所）；INSA Lyon（里昂国立应用科学学院）；CITI（CITI研究所）；UR3720（UR3720实验室）
LOLLA: Deep Reinforcement Learning for Closed-Loop Link Adaptation Towards a GPU-Accelerated AI-RAN
School of Information and Communication Engineering, University of Electronic Science and Technology of China（电子科技大学信息与通信工程学院）；Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China（电子科技大学阳澄湖地区研究院（衢州））；State Key Laboratory of Novel Software Technology, Nanjing University（南京大学软件新技术国家重点实验室）；School of Intelligent Software and Engineering, Nanjing University (Suzhou Campus)（南京大学智能软件与工程学院（苏州校区））
