conftrace_

policy smoothing

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial robustness (2) reinforcement learning (2) reward certification (1) convex optimisation (1) reward lower bound (1) model certification (1) certified bound (1) cooperative multi-agent reinforcement learning (1) cumulative reward (1) robustness certification (1)

Papers

Reward Certification for Policy Smoothed Reinforcement Learning AAAI 2024 Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning AAAI 2023 Policy Smoothing for Provably Robust Reinforcement Learning ICLR 2022