MIDI Lab

In our new preprint 📜(arxiv.org/abs/2302.08560), we show how a number of recent SOTA methods in Reinforcement and Imitation Learning can be unified as RL methods in dual space, utilizing a framework originally proposed by Nachum et al! J/w @yayitsamyzhang , @scottniekum (1/5)

In domains with sparse rewards, reward shaping is well known to speed up learning by providing a dense learning signal. We introduce an alternate method, f-Policy Gradients (arxiv.org/abs/2310.06794…), to obtain optimal policies through distribution matching. (1/n) #NeurIPS2023