SforAiDl / genrl

A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementations with an aim to improve accessibility in RL

https://genrl.readthedocs.io

MIT License

404 stars 59 forks source link

Value iteration #358

Closed hades-rp2010 closed 3 years ago

hades-rp2010 commented 3 years ago

Wrt #357 Havent added a test yet, added the value iteration file as genrl/agents/classical/valueiteration/valueiteration.py. Can be trained with the current Classical trainer

lgtm-com[bot] commented 3 years ago

This pull request introduces 1 alert when merging c02669e4317e54312381cf08c4e7da4c363fde6e into bb85ea19304646ea0210331cac08da94e1e8544c - view on LGTM.com

new alerts:

1 for Unused import

codecov[bot] commented 3 years ago

Codecov Report

Merging #358 into master will increase coverage by 0.04%. The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #358      +/-   ##
==========================================
+ Coverage   90.77%   90.81%   +0.04%     
==========================================
  Files          89       90       +1     
  Lines        3772     3801      +29     
==========================================
+ Hits         3424     3452      +28     
- Misses        348      349       +1

Impacted Files	Coverage Δ
genrl/agents/__init__.py	`100.00% <100.00%> (ø)`
.../agents/classical/valueiteration/valueiteration.py	`100.00% <100.00%> (ø)`
genrl/agents/bandits/multiarmed/epsgreedy.py	`96.29% <0.00%> (-3.71%)`	:arrow_down:
genrl/agents/classical/sarsa/sarsa.py	`96.15% <0.00%> (ø)`

lgtm-com[bot] commented 3 years ago

This pull request introduces 5 alerts when merging d905e54570371f0f7bb14a08b6a66e220eb14d9b into fc4f119ff223e65b505f3037b8077980d596aa77 - view on LGTM.com

new alerts:

5 for Unused import

lgtm-com[bot] commented 3 years ago

This pull request introduces 4 alerts when merging 6a52f0104f476a5e3dec4f8e4420bed8d17533cf into fc4f119ff223e65b505f3037b8077980d596aa77 - view on LGTM.com

new alerts:

4 for Unused import

lgtm-com[bot] commented 3 years ago

This pull request introduces 7 alerts when merging ac0f30cf914ec3beffc09f409758a81d704e5405 into bf208ffc412d12823766f39575d1af96eb2cbc86 - view on LGTM.com

new alerts:

7 for Unused import

lgtm-com[bot] commented 3 years ago

This pull request introduces 1 alert when merging 3377fbe41507d0ddf148d37a78915126d856ec91 into 52b0b4c0399d612c68b705c1e718dfd8e5d22ce3 - view on LGTM.com

new alerts:

1 for Unused import

hades-rp2010 commented 3 years ago

Does the agent train?

It did before, I'll run it again and check

hades-rp2010 commented 3 years ago

Does the agent train?

Yes it does train on FrozenLake

Sharad24 commented 3 years ago

Ok great. Any comparison with Q Learning?

Will merge it post CI re-run