Search Results - RepositoryStats

13

110

apache-2.0

3

Paddle-RLBooks is a reinforcement learning code study guide based on pure PaddlePaddle.

c51 dqn sac td3 ddpg sarsa noisy-dqn nstep-dqn reinforce double-dqn q-learning dueling-dqn actor-critic paddlepaddle policy-gradient value-iteration policy-iteration reinforcement-learning policy-gradient-with-baseline

Created 2021-03-21

24 commits to main branch, last one 3 years ago

18

64

other

2

Reinforcement Learning Short Course

offline-rl q-learning ridesharing deep-q-network model-based-rl policy-gradient value-iteration policy-iteration fitted-q-iteration dynamic-programming monte-carlo-methods policy-based-method off-policy-evaluation reinforcement-learning markov-decision-processes order-dispatch-recommendation temporal-differencing-learning

Created 2023-02-07

90 commits to main branch, last one 4 months ago

11

61

agpl-3.0

5

High Performance Map Matching with Markov Decision Processes (MDPs) and Hidden Markov Models (HMMs).

gis gps graph viterbi map-match q-learning viterbi-hmm map-matching openstreetmap value-iteration graph-algorithms policy-iteration matching-algorithm dynamic-programming hidden-markov-model hidden-markov-models reinforcement-learning markov-decision-process markov-decision-processes

Created 2021-10-12

150 commits to main branch, last one about a month ago

1

25

mit

1

a High-Performance Distributed Solver for Large-Scale Markov Decision Processes (MDP) relying on Inexact Policy Iteration; for Python and C++

cpp mdp mpi ethz petsc python solver python3 nanobind mdpsolver optimization optimal-control policy-iteration dynamic-programming stochastic-optimization markov-decision-processes high-performance-computing stochastic-optimal-control

Created 2024-08-22

554 commits to main branch, last one 20 days ago