MIDI Lab (@lab_midi) header
MIDI Lab (@lab_midi) profile picture

MIDI Lab

@lab_midi

The Machine Intelligence and Decision-making through Interaction Lab @UTAustin led by @yayitsamyzhang. Account run by students.

 Austin, TX
Joined January 2023
  • Tweets3
  • Following15
  • Followers95
Dual RL has been accepted as a spotlight (top 5%) in ICLR 24! Detailed post soon
Harshit Sikchi (@harshit_sikchi) profile pictureHarshit Sikchi
@harshit_sikchi24 Feb 2023
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)
Dual RL: Unification and New Methods for Reinforcement and...

Dual RL: Unification and New Methods for Reinforcement and...

The goal of reinforcement learning (RL) is to find a policy that maximizes the expected cumulative return. It has been shown that this objective can be represented as an optimization problem of...

arxiv.org
3
6
64
9,183
Excited to be at NeurIPS tomorrow! A set of things I will be doing while there you should stop by for: Monday - mentoring at WiML on the topic of reinforcement learning 1/n
1
4
86
17,113
Check out this new work led by @agsidd10! Looking forward to #NeurIPS2023 !!
Siddhant Agarwal (@agsidd10) profile pictureSiddhant Agarwal@agsidd1016 Oct 2023
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/2310.06794v1), to obtain optimal policies through distribution matching. (1/n) #NeurIPS2023
4
970
Load more