Reinforcement Learning
Context-dependent upper-confidence bounds for directed exploration
Raksha Kumaraswamy, Matthew Schlegel, Adam White, Martha White
Second, we t = rt+1+ t+1x>t+1w x>t w , TD-errorforw (see (2)). This t is tobelarger t.
Multi-Agent Common Knowledge Reinforcement Learning
Christian Schroeder de Witt, Jakob Foerster, Gregory Farquhar, Philip Torr, Wendelin Boehmer, Shimon Whiteson
Figure 3: Gamematrices A (top) and B (bottom) [left]. Allexperimentsuse SMACsettingsforcomparability (see Samvelyanetal. (2019) and Appendix Bfordetails).
Recovering from Out-of-sample States via Inverse Dynamics in Offline Reinforcement Learning
However, such pessimism for out-of-sample data could be too restricted and sample inefficient, as not all out-of-sample(unseen) states are not generalizable [20].
Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing
Zehong Hu, Yitao Liang, Jie Zhang, Zhao Li, Yang Liu
Neural Information Processing Systems http://nips.cc/
Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric
While a number of RL methods have been proposed to boost exploration by designing an intrinsic reward signal as exploration bonus.
Diffusion-based ReinforcementLearningvia Q-weightedVariationalPolicyOptimization
UnlikeGaussian policies, the log-likelihood indiffusion policies isinaccessible; thus this entropy term is nontrivial. Moreover, to reduce the large variance of diffusion policies, we also develop an efficient behavior policy through action selection. This can further improve its sample efficiency during online interaction.
MAVEN: Multi-Agent Variational Exploration
Anuj Mahajan, Tabish Rashid, Mikayel Samvelyan, Shimon Whiteson
Wemodel 34], whichisformallyG = hS, U, Pi. S is thestatespacet, every i 2 A {1,..., n} choosesui 2 U which action u 2 U Un. P(s0|s,u): S U S!
Park: An Open Platform for Learning-Augmented Computer Systems
Hongzi Mao, Parimarjan Negi, Akshay Narayan, Hanrui Wang, Jiacheng Yang, Haonan Wang, Ryan Marcus, ravichandra addanki, Mehrdad Khani Shirkoohi, Songtao He, Vikram Nathan, Frank Cangialosi, Shaileshh Venkatakrishnan, Wei-Hung Weng, Song Han, Tim Kraska, Dr.Mohammad Alizadeh
Neural Information Processing Systems http://nips.cc/
Reduced Policy Optimization for Continuous Control with Hard Constraints Shutong Ding 1 Jingya Wang 1 Yali Du2Y e Shi 1 1
Recent advances in constrained reinforcement learning (RL) have endowed reinforcement learning with certain safety guarantees.