Skip to content
conftrace_

reward mixing

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

latent context (1) starcraft ii (1) partially observable mdp (1) latent state (1) credit assignment (1) intrinsic reward (1) reward shaping (1) contextual bandit (1) efficient exploration (1) optimal policy (1)

Papers

Reward-Mixing MDPs with Few Latent Contexts are Learnable ICML 2023 AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network ACML 2022 Reinforcement Learning in Reward-Mixing MDPs NeurIPS 2021