Skip to content

Actions: vladfi1/slippi-ai

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
43 workflow runs
43 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Log regret vs optimal policy.
slippi-ai test cases #43: Commit ddf4df9 pushed by vladfi1
October 2, 2024 11:36 4m 19s q-learning
October 2, 2024 11:36 4m 19s
Optimize q_policy's expected advantage.
slippi-ai test cases #42: Commit c947cae pushed by vladfi1
October 2, 2024 11:27 4m 22s q-learning
October 2, 2024 11:27 4m 22s
Overwrite network config when restoring in imitation.
slippi-ai test cases #41: Commit 1745377 pushed by vladfi1
October 1, 2024 21:08 4m 51s main
October 1, 2024 21:08 4m 51s
Fix reward hacking stats.
slippi-ai test cases #40: Commit 4a098f2 pushed by vladfi1
October 1, 2024 19:00 2m 28s reward-hacking
October 1, 2024 19:00 2m 28s
Penalize stalling offstage.
slippi-ai test cases #39: Commit 12c7242 pushed by vladfi1
October 1, 2024 18:17 2m 33s reward-hacking
October 1, 2024 18:17 2m 33s
Log player stats in train_two.
slippi-ai test cases #38: Commit 17d4b12 pushed by vladfi1
October 1, 2024 16:47 2m 10s reward-hacking
October 1, 2024 16:47 2m 10s
Overwrite network config when restoring in imitation.
slippi-ai test cases #37: Commit 1745377 pushed by vladfi1
October 1, 2024 16:27 4m 45s jit-compile
October 1, 2024 16:27 4m 45s
Penalize ledge grabs.
slippi-ai test cases #36: Commit d394986 pushed by vladfi1
October 1, 2024 15:41 2m 17s reward-hacking
October 1, 2024 15:41 2m 17s
Test imitation on GRU.
slippi-ai test cases #35: Commit c20ff4d pushed by vladfi1
October 1, 2024 15:17 2m 19s jit-compile
October 1, 2024 15:17 2m 19s
jit-compile agents
slippi-ai test cases #34: Commit 442e398 pushed by vladfi1
October 1, 2024 14:59 4m 29s jit-compile
October 1, 2024 14:59 4m 29s
Better rel_v_loss.
slippi-ai test cases #33: Commit 0fda6a7 pushed by vladfi1
October 1, 2024 14:15 4m 29s q-learning
October 1, 2024 14:15 4m 29s
jit_compile q-learning to increase speed (and avoid OOM?)
slippi-ai test cases #32: Commit 12e9ce2 pushed by vladfi1
October 1, 2024 09:51 4m 36s q-learning
October 1, 2024 09:51 4m 36s
Improve test case.
slippi-ai test cases #31: Commit f3def9f pushed by vladfi1
October 1, 2024 09:51 4m 32s q-learning-dbg
October 1, 2024 09:51 4m 32s
disable_audio command-line option
slippi-ai test cases #30: Commit 2c44933 pushed by vladfi1
September 30, 2024 18:46 4m 13s main
September 30, 2024 18:46 4m 13s
jit_compile q-learning to increase speed (and avoid OOM?)
slippi-ai test cases #29: Commit b658f6e pushed by vladfi1
September 30, 2024 16:30 4m 34s q-learning
September 30, 2024 16:30 4m 34s
Initialize sample/q policies from imitation.
slippi-ai test cases #28: Commit 9e4e1d8 pushed by vladfi1
September 30, 2024 11:22 4m 16s q-learning
September 30, 2024 11:22 4m 16s
Improve test case.
slippi-ai test cases #27: Commit e293704 pushed by vladfi1
September 29, 2024 19:21 1m 51s q-learning-dbg
September 29, 2024 19:21 1m 51s
checkpoint
slippi-ai test cases #26: Commit bead399 pushed by vladfi1
September 29, 2024 19:07 1m 50s q-learning-dbg
September 29, 2024 19:07 1m 50s
Fix minor bug in BasicAgent.multi_sample.
slippi-ai test cases #25: Commit aca2e1a pushed by vladfi1
September 28, 2024 15:54 4m 32s main
September 28, 2024 15:54 4m 32s
snapshot
slippi-ai test cases #24: Commit 7212e0d pushed by vladfi1
September 28, 2024 14:23 4m 11s q-learning
September 28, 2024 14:23 4m 11s
Train sample/q policies together with q-function.
slippi-ai test cases #23: Commit 12c40fc pushed by vladfi1
September 26, 2024 21:01 4m 16s q-learning
September 26, 2024 21:01 4m 16s
Optimize/track reverse teacher-KL during RL.
slippi-ai test cases #22: Commit 010c0da pushed by vladfi1
September 26, 2024 10:24 4m 32s main
September 26, 2024 10:24 4m 32s
Don't use fake data in with-dolphin tests.
slippi-ai test cases #21: Commit 8583171 pushed by vladfi1
September 25, 2024 12:17 4m 38s github-actions
September 25, 2024 12:17 4m 38s
Update rl_demo
slippi-ai test cases #20: Commit 9cf9650 pushed by vladfi1
September 25, 2024 12:10 4m 28s github-actions
September 25, 2024 12:10 4m 28s
manifest
slippi-ai test cases #19: Commit 141de3e pushed by vladfi1
September 25, 2024 11:59 2m 56s github-actions
September 25, 2024 11:59 2m 56s