Search Results - RepositoryStats

rl-starter-files lcswillems

181

633

mit

15

RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code

a2c a3c ppo pytorch minigrid multi-process reward-shaping preprocessed-observations

Created 2018-04-11

497 commits to master branch, last one about a year ago

MultiHopKG salesforce

71

298

bsd-3-clause

14

Multi-hop knowledge graph reasoning learned via policy gradient with reward shaping and action dropout

pytorch action-dropout reward-shaping knowledge-graph policy-gradient multi-hop-reasoning reinforcement-learning

Created 2018-09-26

29 commits to master branch, last one 3 months ago

torch-ac lcswillems

64

190

mit

8

Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO

a2c a3c ppo pytorch minigrid recurrent actor-critic multi-process reward-shaping advantage-actor-critic reinforcement-learning recurrent-neural-networks deep-reinforcement-learning proximal-policy-optimization

Created 2019-04-07

25 commits to master branch, last one about a year ago

NeuOpt yining043

2

31

mit

1

This repo implements our paper, "Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt", which has been accepted at NeurIPS 2023.

tsp vrp k-opt transformer reward-shaping learning-to-optimize reinforcement-learning vehicle-routing-problem deep-reinforcement-learning neural-combinatorial-optimization

Created 2023-08-09

18 commits to main branch, last one 5 days ago

ARP csmile-1006

1

31

mit

1

Guide Your Agent with Adaptive Multimodal Rewards (NeurIPS 2023 Accepted)

robotics deep-learning reward-shaping vision-language imitation-learning reinforcement-learning

Created 2023-09-06

10 commits to master branch, last one 9 months ago