Bayesian Transfer Reinforcement Learning with Prior Knowledge Rules

Titsias, Michalis K.; Nikoloutsopoulos, Sotirios

doi:10.48550/arxiv.1810.00468

Cited by 2 publications

(3 citation statements)

References 3 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, incorporating prior knowledge as constraints or loss functions for conventional machine learning algorithms. Since current breakthroughs on games are mostly relying on reinforcement learning which is low sample efficient, how to achieve sample efficient reinforcement learning based on human knowledge is a future direction [55], [56].…”

Section: Low Resources Aimentioning

confidence: 99%

AI in Human-computer Gaming: Techniques, Challenges and Opportunities

Yin¹,

Yang²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

With breakthrough of AlphaGo, AI in human-computer game has become a very hot topic attracting researchers all around the world, which usually serves as an effective standard for testing artificial intelligence. Various game AI systems (AIs) have been developed such as Libratus, OpenAI Five and AlphaStar, beating professional human players. In this paper, we survey recent successful game AIs, covering board game AIs, card game AIs, first-person shooting game AIs and real time strategy game AIs. Through this survey, we 1) compare the main difficulties among different kinds of games for the intelligent decision making field ; 2) illustrate the mainstream frameworks and techniques for developing professional level AIs; 3) raise the challenges or drawbacks in the current AIs for intelligent decision making; and 4) try to propose future trends in the games and intelligent decision making techniques. Finally, we hope this brief review can provide an introduction for beginners, inspire insights for researchers in the filed of AI in games.

show abstract

Section: Low Resources Aimentioning

confidence: 99%

AI in Human-computer Gaming: Techniques, Challenges and Opportunities

Yin¹,

Yang²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This idea is inspired by the BDQ architecture [24] and extended to PG methods. In particular, this allows us to define Bayesian policies and incorporate prior information about the MA problem into the DRL agent [32].…”

Section: B Contributions and Outlinementioning

confidence: 99%

“…In order to incorporate this prior knowledge into the RL agent, we introduce a Bayesian policy inspired by [32]. We express the posterior policy q(a|A; θ π ) as a function of the prior over the agent state f (a; A) and the task specific policy π(a|A; θ π ) parameterized by θ π with the Bayes rule:…”

Section: B Exploiting Prior Knowledgementioning

confidence: 99%

Deep Reinforcement Learning for Scheduling Uplink IoT Traffic with Strict Deadlines

Robaglia

Destounis

Coupechoux

et al. 2021

2021 IEEE Global Communications Conference (GLOBECOM)

View full text Add to dashboard Cite

This article addresses the problem of Ultra Reliable Low Latency Communications (URLLC) in wireless networks, a framework with particularly stringent constraints imposed by many Internet of Things (IoT) applications from diverse sectors. We propose a novel Deep Reinforcement Learning (DRL) scheduling algorithm, named NOMA-PPO, to solve the Non-Orthogonal Multiple Access (NOMA) uplink URLLC scheduling problem involving strict deadlines. The challenge of addressing uplink URLLC requirements in NOMA systems is related to the combinatorial complexity of the action space due to the possibility to schedule multiple devices, and to the partial observability constraint that we impose to our algorithm in order to meet the IoT communication constraints and be scalable.Our approach involves 1) formulating the NOMA-URLLC problem as a Partially Observable Markov Decision Process (POMDP) and the introduction of an agent state, serving as a sufficient statistic of past observations and actions, enabling a transformation of the POMDP into a Markov Decision Process (MDP); 2) adapting the Proximal Policy Optimization (PPO) algorithm to handle the combinatorial action space; 3) incorporating prior knowledge into the learning agent with the introduction of a Bayesian policy. Numerical results reveal that not only does our approach outperform traditional multiple access protocols and DRL benchmarks on 3GPP scenarios, but also proves to be robust under various channel and traffic configurations, efficiently exploiting inherent time correlations.

show abstract

Bayesian Transfer Reinforcement Learning with Prior Knowledge Rules

Cited by 2 publications

References 3 publications

AI in Human-computer Gaming: Techniques, Challenges and Opportunities

AI in Human-computer Gaming: Techniques, Challenges and Opportunities

Deep Reinforcement Learning for Scheduling Uplink IoT Traffic with Strict Deadlines

Contact Info

Product

Resources

About