SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning

แชร์
ฝัง
  • เผยแพร่เมื่อ 2 ธ.ค. 2024

ความคิดเห็น • 22

  • @deltax7159
    @deltax7159 6 หลายเดือนก่อน +7

    you guys are so brilliant. such a great idea, would love to hear a podcast with you guys talking about how you came up with these ideas/ the life cycle of SINDY rl.

  • @musicarroll
    @musicarroll 6 หลายเดือนก่อน +3

    Nick: Excellent work! This is genuine progress in AI to integrate state estimation SOTA with decision making (RL). Would love to see this further refined using POMDPs ( Partially Oberservable Markov Decision Processes).

    • @sai4007
      @sai4007 6 หลายเดือนก่อน

      Checkout PlaNet and dreamer models

  • @Idonai
    @Idonai 6 หลายเดือนก่อน +3

    Thanks for the presentation. Do I understand correctly that this whole process could be automated making highly efficient agents or do some aspects of this process require manual work? Also, how well does it scale to significantly harder RL problems? Does this technique stay computationally efficient (e.g. compared to PPO) in these harder ernvironments? Could this be combined with Reinforcement learning from human feedback (RLHF) in a practical manner?

  • @jimlbeaver
    @jimlbeaver 6 หลายเดือนก่อน +3

    Great presentation, very interesting approach. I’m curious about the intuition behind the ensemble…eager to read more. Thanks!

    • @Eigensteve
      @Eigensteve  6 หลายเดือนก่อน +1

      Thanks Jim! The ensembling gives us way more robustness to noisy data and also to very few data samples, so it can let us train models much more quickly than NN models.

  • @JoshuaSheppard-pp5iz
    @JoshuaSheppard-pp5iz 6 หลายเดือนก่อน

    Bold steps ... thrilling work! I look forward to working through the implementation.

  • @brianarbuckle2284
    @brianarbuckle2284 6 หลายเดือนก่อน +1

    Great work. This is fantastic!

  • @TheRubencho176
    @TheRubencho176 6 หลายเดือนก่อน

    Impressive! Thank you very much for sharing and for the inspiration.

  • @drj92
    @drj92 6 หลายเดือนก่อน +2

    Has your lab considered experimenting with Kolmogorov-Arnold Networks in combination with SINDy? It feels like a potentially excellent match.
    Their approach to network sparsification, in particular, seems like it could be automated in a very interesting way via SINDy. In the recent paper they fix and prune activation functions by hand, but it seems that you could instead use SINDy to automatically fix a particular activation function once it fit a dictionary term beyond some threshold.
    Love the presentation!

    • @Eigensteve
      @Eigensteve  6 หลายเดือนก่อน +1

      Neat idea -- definitely thinking about ways of connecting these topics. Thanks!

  • @xueqiu6384
    @xueqiu6384 5 หลายเดือนก่อน

    curious about how fitting can accelerate the training process. Any assumptions for action space/ state space / environment? Thanks for your attention.

  • @srikanthtupurani6316
    @srikanthtupurani6316 6 หลายเดือนก่อน +2

    This is so amazing I don't have words. Deepmind made computers play go game, chess game. It uses reinforcement learning. It is simply superb.

  • @ClicheKHFan
    @ClicheKHFan 6 หลายเดือนก่อน

    Amazing. I've been looking for something like this.

  • @awsomeguy563
    @awsomeguy563 6 หลายเดือนก่อน

    Absolutely brilliant

  • @Student-ve5ug
    @Student-ve5ug 6 หลายเดือนก่อน

    Dear Sir,
    If we want to use reinforcement learning (RL) in a specific environment, I am concerned that the trial-and-error method will result in many errors, some of which may have negative consequences. Furthermore, I am unsure how many attempts the RL model will need to reach the optimal and correct decision. How can this challenge be addressed?

  • @nvjt101
    @nvjt101 6 หลายเดือนก่อน +3

    Real AI is RL

  • @Pedritox0953
    @Pedritox0953 6 หลายเดือนก่อน

    Great video!

  • @kevinarancibiacalderon9039
    @kevinarancibiacalderon9039 6 หลายเดือนก่อน

    Gracias por el video!

  • @alexxxcanz
    @alexxxcanz 6 หลายเดือนก่อน

    Great!

  • @SrZonne
    @SrZonne 6 หลายเดือนก่อน

    Amazing

  • @juleswombat5309
    @juleswombat5309 6 หลายเดือนก่อน

    Interesting