1. X
  2. Oswin So
Log inSign up
Oswin So
50 posts
user avatar
Oswin So
@oswinso
Graduate Researcher with Chuchu Fan at MIT @mit_REALM. Bringing Guarantees to Safe Reinforcement Learning 🇭🇰
Cambridge, Massachusetts
oswinso.xyz
Joined April 2013
111
Following
164
Followers
RepliesRepliesMediaMedia
  • user avatar
    Oswin So
    @oswinso
    Dec 2, 2025
    At #NeurIPS from Dec 2 to Dec 7 in San Diego! Looking forward to catching up and meeting new friends. Excited to chat about safety for robotics, constraint satisfaction in RL, and (stochastic) optimal control. Feel free to DM me to grab coffee or have a chat!
  • user avatar
    Oswin So
    @oswinso
    Nov 7, 2023
    Suppose now that Xₜ is started from ε: Xₜ ≔ ε + ∫₀ᵗ 1{Wₛ >= 0} dWₛ Since Xₜ = ε + max(W_t,0) - ½ L(t) and L(t) strictly increases only when Wₜ=0, does there exist a time u such that Xᵤ ≥ Wᵤ AND Xᵤ < 0?
    user avatar
    Oswin So
    @oswinso
    Nov 5, 2023
    More observations and questions on the following stochastic integral: Xₜ ≔ ∫₀ᵗ 1{Wₛ >= 0} dWₛ Numerically simulating this does confirm that E[Xₜ]=0 and Xₜ does go negative. What I did not expect, however, is the distribution of Xₜ to look the way it does.
    Image
  • user avatar
    Oswin So
    @oswinso
    Nov 5, 2023
    More observations and questions on the following stochastic integral: Xₜ ≔ ∫₀ᵗ 1{Wₛ >= 0} dWₛ Numerically simulating this does confirm that E[Xₜ]=0 and Xₜ does go negative. What I did not expect, however, is the distribution of Xₜ to look the way it does.
    Image
    user avatar
    Oswin So
    @oswinso
    Nov 1, 2023
    Small question about Ito integrals: Consider Xₜ ≔ ∫₀ᵗ 1{Wₛ >= 0} dWₛ where Wₜ is a Brownian Motion and 1 is the indicator. Xₜ is a martingale, so E[Xₜ] = 0. I would think that Xₜ is non-negative, but that doesn't seem to be true?
  • user avatar
    Oswin So
    @oswinso
    Nov 1, 2023
    Small question about Ito integrals: Consider Xₜ ≔ ∫₀ᵗ 1{Wₛ >= 0} dWₛ where Wₜ is a Brownian Motion and 1 is the indicator. Xₜ is a martingale, so E[Xₜ] = 0. I would think that Xₜ is non-negative, but that doesn't seem to be true?
  • user avatar
    Oswin So
    @oswinso
    Jul 12, 2023
    Epigraph form provides a stable way of solving constrained optimal control problems to find safe, stabilizing controllers. We investigate this in our work accepted to #RSS2023. Project: mit-realm.github.io/efppo Paper: arxiv.org/pdf/2305.14154… MIT News: news.mit.edu/2023/safe-and-…
    Image
    GIF

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement