conftrace_

state-action distribution

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

game-theoretic reformulation (1) policy compatibility (1) policy space compression (1) representative policies (1) set cover problem (1) diverse behavior (1) population-based training (1) rényi divergence (1) doubly robust (1) doubly robust estimator (1)

Papers

Generating Diverse Cooperative Agents by Learning Incompatible Policies ICLR 2023 Reward-Free Policy Space Compression for Reinforcement Learning AISTATS 2022 SOPE: Spectrum of Off-Policy Estimators NeurIPS 2021 Generative predecessor models for sample-efficient imitation learning ICLR 2019