Dynamic Programming and Optimal Control, Volume I

Bertsekas, D. P. (2017). Dynamic Programming and Optimal Control, Volume I.

Type

Book

Intellectual base

Review or monograph

Year

2017

ISBN

9781886529434

Link

http://athenasc.com/dpbook.html

Cited from

operations_research

Cited by

2 citations across 2 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Dynamic Programming
  • In the approximate-DP and deep-RL extensions, function approximation replaces explicit tabulation to scale to state spaces that remain combinatorially vast — trading exactness for applicability at industrial scale.

    This sourceAthena Scientific, Belmont, MA. ISBN 9781886529434. Leading reference on DP for optimal control and sequential decision-making: finite-horizon backward induction, infinite-horizon value/policy iteration, and (Ch. 6) approximate DP with parametric/neural value-function approximation and rollout

• Markov Decision Processes (MDPs)
  • … Ray RLlib, TF-Agents, CleanRL, RL4LMs); POMDP libraries (pomdp_py, POMDPs.jl, SARSOP); simulation environments (OpenAI Gym, PettingZoo, DeepMind Control Suite, Isaac Gym, Gymnasium); and textbook literature (Puterman 1994 as the canonical OR MDP reference; Sutton and Barto (2018) for the RL perspective; Bertsekas

    This sourceAthena Scientific. Standard reference on dynamic programming and stochastic optimal control covering deterministic and stochastic MDP formulations, approximation methods, and the bridge to neuro-dynamic programming and modern RL.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:c6482988c51f · see in the full table