Skip to content

Actions: pytorch/rl

Generate documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
4,291 workflow runs
4,291 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Feature] Log each entropy for composite distributions in PPO
Generate documentation #10954: Pull request #2707 opened by louisfaury
January 20, 2025 14:45 Action required louisfaury:lf/ppo-log-composite-entropies
January 20, 2025 14:45 Action required
[CI] workflow permissions
Generate documentation #10953: Pull request #2706 opened by vmoens
January 20, 2025 13:28 40m 30s gh/vmoens/72/head
January 20, 2025 13:28 40m 30s
[Example] Using Collector's device args
Generate documentation #10952: Commit 539c215 pushed by vmoens
January 20, 2025 13:23 2s main
January 20, 2025 13:23 2s
[Example] Using Collector's device args
Generate documentation #10951: Pull request #2705 opened by vmoens
January 20, 2025 13:20 1s gh/vmoens/74/head
January 20, 2025 13:20 1s
[BugFix] Fix device transfer for collectors with init_random_frames mixed devices
Generate documentation #10950: Pull request #2704 opened by vmoens
January 20, 2025 11:59 1s gh/vmoens/73/head
January 20, 2025 11:59 1s
[BugFix] Fix partial device transfers in collector
Generate documentation #10949: Pull request #2703 opened by vmoens
January 20, 2025 11:59 2s gh/vmoens/72/head
January 20, 2025 11:59 2s
[BugFix] patch rand_action in TransformedEnv to read the base_env method
Generate documentation #10948: Pull request #2699 synchronize by vmoens
January 17, 2025 18:13 2s gh/vmoens/68/head
January 17, 2025 18:13 2s
[Feature] example_data for NonTensor spec
Generate documentation #10947: Pull request #2698 synchronize by vmoens
January 17, 2025 18:13 1s gh/vmoens/67/head
January 17, 2025 18:13 1s
[Feature] UnaryTransform for input entries
Generate documentation #10946: Pull request #2700 synchronize by vmoens
January 17, 2025 18:13 1s gh/vmoens/69/head
January 17, 2025 18:13 1s
[Feature,Refactor] Chess improvements: fen, pgn, pixels, san
Generate documentation #10945: Pull request #2702 synchronize by vmoens
January 17, 2025 18:13 2s gh/vmoens/71/head
January 17, 2025 18:13 2s
[Feature,Refactor] Chess improvements: fen, pgn, pixels, san
Generate documentation #10944: Pull request #2702 opened by vmoens
January 17, 2025 13:29 1s gh/vmoens/71/head
January 17, 2025 13:29 1s
[Feature] Tokenizer transform
Generate documentation #10943: Pull request #2701 opened by vmoens
January 17, 2025 13:29 2s gh/vmoens/70/head
January 17, 2025 13:29 2s
[Feature] UnaryTransform for input entries
Generate documentation #10942: Pull request #2700 opened by vmoens
January 17, 2025 13:29 2s gh/vmoens/69/head
January 17, 2025 13:29 2s
[BugFix] patch rand_action in TransformedEnv to read the base_env method
Generate documentation #10941: Pull request #2699 opened by vmoens
January 17, 2025 13:29 1s gh/vmoens/68/head
January 17, 2025 13:29 1s
[Feature] example_data for NonTensor spec
Generate documentation #10940: Pull request #2698 opened by vmoens
January 17, 2025 13:29 1s gh/vmoens/67/head
January 17, 2025 13:29 1s
[Doc] Add Stack transform link in docs (#2689)
Generate documentation #10939: Commit c5f1565 pushed by vmoens
January 16, 2025 11:25 46m 15s main
January 16, 2025 11:25 46m 15s
[Refactor] Use default device instead of CPU in losses
Generate documentation #10938: Commit c3b9d1d pushed by vmoens
January 16, 2025 11:24 43m 17s main
January 16, 2025 11:24 43m 17s
[Feature] Make PPO compatible with composite actions and log-probs
Generate documentation #10937: Commit 256a700 pushed by vmoens
January 16, 2025 11:15 41m 45s main
January 16, 2025 11:15 41m 45s
[Feature] Make PPO compatible with composite actions and log-probs
Generate documentation #10936: Pull request #2665 synchronize by vmoens
January 16, 2025 11:11 43m 31s gh/vmoens/58/head
January 16, 2025 11:11 43m 31s
[WIP] Compute lp during loss execution
Generate documentation #10935: Pull request #2688 synchronize by vmoens
January 16, 2025 11:11 41m 36s gh/vmoens/66/head
January 16, 2025 11:11 41m 36s
[Refactor] Use default device instead of CPU in losses
Generate documentation #10934: Pull request #2687 synchronize by vmoens
January 16, 2025 11:11 41m 6s gh/vmoens/65/head
January 16, 2025 11:11 41m 6s
[Refactor] Use default device instead of CPU in losses
Generate documentation #10933: Pull request #2687 synchronize by vmoens
January 15, 2025 21:11 7m 8s gh/vmoens/65/head
January 15, 2025 21:11 7m 8s
[WIP] Compute lp during loss execution
Generate documentation #10932: Pull request #2688 synchronize by vmoens
January 15, 2025 21:11 6m 42s gh/vmoens/66/head
January 15, 2025 21:11 6m 42s
[Feature] Make PPO compatible with composite actions and log-probs
Generate documentation #10931: Pull request #2665 synchronize by vmoens
January 15, 2025 21:11 6m 23s gh/vmoens/58/head
January 15, 2025 21:11 6m 23s
[BugFix,Doc] Fix BATCHED_PIPE_TIMEOUT refs and doc
Generate documentation #10930: Commit dc25a55 pushed by vmoens
January 15, 2025 21:06 6m 21s main
January 15, 2025 21:06 6m 21s