conftrace_

pessimistic optimization

4 papers

Explore in graph

Co-occurring keywords

offline reinforcement learning (492) q-value function (6) pessimistic estimation (4) concentration bound (28) dual gradient ascent (2) network simulation (8) pessimistic adjustment (2) traffic distribution (4) pessimistic dual value iteration (1) pessimistic value (1)

Papers

Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model NIPS 2024
Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning NIPS 2024
NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation NIPS 2024
Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration NIPS 2021