Results 11 to 20 of about 6,930,474 (290)
State-Constrained Offline Reinforcement Learning [PDF]
CoRRTraditional offline reinforcement learning methods predominantly operate in a batch-constrained setting. This confines the algorithms to a specific state-action distribution present in the dataset, reducing the effects of distributional shift but ...
Jin, Yue +2 more
core +5 more sources
Reinforcement Learning-based Spectrum Sharing for Cognitive Radio [PDF]
, 2011 This thesis investigates how distributed reinforcement learning-based resource assignment algorithms can be used to improve the performance of a cognitive radio system.
Jiang, Tao
core +6 more sources
Improving Exploration in Reinforcement Learning through Domain Knowledge and Parameter Analysis [PDF]
, 2010 This thesis presents novel work on how to improve exploration in reinforcement learning using domain knowledge and knowledge-based approaches to reinforcement learning.
Grzes, Marek
core +7 more sources
Comparing policy gradient and value function based reinforcement learning methods in simulated electrical power trade [PDF]
, 2012 In electrical power engineering, reinforcement learning algorithms can be used to model the strategies of electricity market participants. However, traditional value function based reinforcement learning algorithms suffer from convergence issues when ...
Burt, Graeme +3 more
core +4 more sources
Robust Constrained Reinforcement Learning
CoRR, 2022 Constrained reinforcement learning is to maximize the expected reward subject to constraints on utilities/costs. However, the training environment may not be the same as the test one, due to, e.g., modeling error, adversarial attack, non-stationarity, resulting in severe performance degradation and more importantly constraint violation.
Yue Wang 0068, Fei Miao, Shaofeng Zou
openaire +2 more sources
Anytime-Constrained Reinforcement Learning
CoRR, 2023 We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in time, almost surely. Although Markovian policies are no longer sufficient, we show that there exist optimal deterministic policies augmented with cumulative costs.
Jeremy McMahan, Xiaojin Zhu 0001
openaire +3 more sources
Resilient Constrained Reinforcement Learning
CoRR, 2023 We study a class of constrained reinforcement learning (RL) problems in which multiple constraint specifications are not identified before training. It is challenging to identify appropriate constraint specifications due to the undefined trade-off between the reward maximization objective and the constraint satisfaction, which is ubiquitous in ...
Dongsheng Ding +2 more
openaire +4 more sources
Reachability Constrained Reinforcement Learning
CoRR, 2022 Constrained reinforcement learning (CRL) has gained significant interest recently, since safety constraints satisfaction is critical for real-world problems. However, existing CRL methods constraining discounted cumulative costs generally lack rigorous definition and guarantee of safety.
Dongjie Yu +3 more
openaire +4 more sources
Density Constrained Reinforcement Learning
CoRR, 2021 We study constrained reinforcement learning (CRL) from a novel perspective by setting constraints directly on state density functions, rather than the value functions considered by previous works. State density has a clear physical and mathematical interpretation, and is able to express a wide variety of constraints such as resource limits and safety ...
Qin, Zengyi, Chen, Yuxiao, Fan, Chuchu
openaire +4 more sources
Advances in Neural Information Processing Systems 35, 2022 NeurIPS ...
Whiyoung Jung +3 more
openaire +4 more sources