ShortestPathWalkerHeuristicPolicy (316a40d0) · Commits · manavsinghal157 / marl-flatland · GitLab

Skip to content

GitLab

Explore

Sign in

Primary navigation

Project

M

marl-flatland
- Activity
- Members
- Labels
- Issues
- Issue boards
- Milestones
- Wiki
- Terraform modules
- Incidents

Snippets Groups Projects

316a40d0

Commit 316a40d0 authored 4 years ago by Egli Adrian (IT-SCI-API-PFI)

Downloads
- Patches
- Plain Diff

ShortestPathWalkerHeuristicPolicy

parent f310811b

No related branches found

No related tags found

No related merge requests found

Changes 9

Hide whitespace changes

Inline Side-by-side

Showing

checkpoints/201124171810-7800.pth.local 0 additions, 0 deletions

checkpoints/201124171810-7800.pth.local
checkpoints/201124171810-7800.pth.target 0 additions, 0 deletions

checkpoints/201124171810-7800.pth.target
reinforcement_learning/dddqn_policy.py 4 additions, 2 deletions

reinforcement_learning/dddqn_policy.py
reinforcement_learning/multi_agent_training.py 104 additions, 56 deletions

reinforcement_learning/multi_agent_training.py
reinforcement_learning/ppo/ppo_agent.py 8 additions, 0 deletions

reinforcement_learning/ppo/ppo_agent.py
run.py 37 additions, 15 deletions

run.py
utils/dead_lock_avoidance_agent.py 16 additions, 2 deletions

utils/dead_lock_avoidance_agent.py
utils/extra.py 3 additions, 2 deletions

utils/extra.py
utils/fast_tree_obs.py 29 additions, 17 deletions

utils/fast_tree_obs.py

with 201 additions and 94 deletions

Loading

0% Loading or .

You are about to add 0 people to the discussion. Proceed with caution.

Finish editing this message first!

Please register or sign in to comment