RT @simoptim: @DBertsekas Agree. When an appropriate feature space is constructed, aggregation methods often outperform neural networks. I’….

Sharing my new paper (joint with Yuchao Li and Kim Hammar) on Feature-Based Belief Aggregation for Partially Observable Markov Decision Problems," The paper gives favorable computational results involving very large scale problems.#ReinforcementLearning.

I am pleased to share at slides, podcast and an essay on my lecture:. “Ten Simple Rules for Mathematical Writing”. Since its original delivery in a slide presentation at MIT (2002), it has been referenced widely and used in mathematical writing courses.

I am pleased to share my new paper (joint with Yuchao Li) on .Error Bounds for Aggregation Methods. In my view, aggregation is an under-appreciated off-line training approach in #reinforcementlearning.

I am pleased to share the link to my videolecture from 5/2/2025, at Harvard University:.Reinforcement Learning, Model Predictive Control, and Newton's Method for Solving Bellman's equation .Slides at

I am pleased to share at High quality AI-generated podcast links for my books:.1) Lessons from AlphaZero . 2) Parallel and Distributed Computation.See for PDF copies.#reinforcementlearning#machinelearning.

I am pleased to share podcasts (<30 mins) describing two of my books:.Neuro-Dynamic Programming. A Course in Reinforcement Learning.Free PDF of both books can be found at

RL is an older name for a much broader AI methodology, that does not connect well to the present content of the field (what are you reinforcing?) We thought Neuro-Dynamic Programming is a more descriptive name (the marriage of DP theory and NN technology).

A free PDF of the 1996 Neuro-Dynamic Programming book by myself and John Tsitsiklis, the 1st book in #reinforcementlearning, has been posted at An AI-generated podcast that summarizes the book can be found at

I am often asked about the relative merits of various #reinforcementlearning approaches, such as policy gradient and value-based methods. The last lecture of my RL course deals with this question, and related training issues, see:.

Thanks to @AntoMon for this thoughtful review!.

I am pleased to share a review of my book "A course in reinforcement learning" (2nd edition) This is the textbook for my RL course at ASU (free PDF at .#reinforcementlearning #machinelearning.

I am pleased to share the full set of videolectures, slides, textbook, and other supporting material of the 7th offering of my Reinforcement Learning class at ASU, which was completed two days ago; check

I am pleased to share the video from my yesterday's lecture "Abstract Dynamic Programming, Reinforcement Learning, Newton's Method, and Gradient Optimization" at the ASU Math Dept.This is an overview lecture on the relations between DP and RL.

A free PDF of my book "Rollout, Policy Iteration, and #ReinforcementLearning " has been posted at my web site An extensive research account on rollout algorithms, including multiagent rollout, and the connection with Newton's method.

RT @KimHammar1: A recording of my guest lecture at ASU on aggregation for approximating POMDPs is available here: .

Just posted a videolecture on a Viterbi-like rollout/#reinforcementlearning algorithm for most likely sequence generation in Markov chains, and HMM inference, at Applies to large state spaces where the Viterbi algorithm is intractable.

RT @tomssilver: This week's #PaperILike is "Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Progr….

A video lecture on #reinforcementlearning was posted at Originally delivered at an IEEE Symposium on ADPRL, Orlando, 2014. Several of the ideas await further exploration. Slides at

RT @victor_explore: This is an amazing playlist to learn Reinforcement Learning by Dimitri Bertsekas