conftrace_

configurable markov decision process

3 papers

Explore in graph

Also known as

CONF-MDP

Co-occurring keywords · papers mentioning both

safe policy-model iteration (1) environment configuration (1) relative entropy model policy search (1) multi-agent system (1) configurable mdp (1) non-cooperative setting (1) trust region method (1) joint optimization (1) continuous domain (1) regret bound (1)

Papers

Learning in Non-Cooperative Configurable Markov Decision Processes NeurIPS 2021 Reinforcement Learning in Configurable Continuous Environments ICML 2019 Configurable Markov Decision Processes ICML 2018