ruizhaogit

music. Mutual Information State Intrinsic Control (ICLR 2021 Spotlight)

EnergyBasedPrioritization. Energy-Based Hindsight Experience Prioritization (CoRL 2018) Oral presentation (7%)

maximum_entropy_population_based_training. Maximum Entropy Population Based Training for Zero-Shot Human-AI Coordination

mep. Maximum Entropy-Regularized Multi-Goal Reinforcement Learning (ICML 2019)

GuessWhat-TemperedPolicyGradient. Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient (SLT 2018) (IJCAIw 2018)

MNIST-GuessNumber. Efficient Dialog Policy Learning via Positive Memory Retention (SLT 2018) (NIPSw 2018)

PositiveMemoryRetention. Efficient Dialog Policy Learning via Positive Memory Retention (SLT 2018) (NIPSw 2018)

alf. Agent Learning Framework https://alf.readthedocs.io