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!
Graduate Researcher with Chuchu Fan at MIT @mit_REALM. Bringing Guarantees to Safe Reinforcement Learning ðŸ‡ðŸ‡°
- 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?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.
- 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.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?
- 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?
- 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-…

