Michel Aractingi 04cbf669cf fix(sac): make temperature a property to fix checkpoint resume bug (#2877) ...

* fix(sac): make temperature a property to fix checkpoint resume bug

Temperature was stored as a plain float and not restored after loading
a checkpoint, causing incorrect loss computations until update_temperature()
was called. Changed to a property that always computes from log_alpha,
ensuring correct behavior after checkpoint loading.

* simplify docstrings

2026-01-30 12:23:22 +01:00

..

groot

feat(policies): add Nvidia Gr00t N1.5 model (#2292)

2025-10-23 13:50:30 +02:00

hilserl

chore: replace hard-coded next values with constants throughout all the source code (#2056)

2025-09-26 14:30:07 +02:00

pi0_fast

feat(policies): add autoregressive VLAs with tokenization PiFast (#2734)

2026-01-09 23:08:37 +01:00

pi0_pi05

[RTC] Real Time Chunking for Pi0, Smolvla, Pi0.5 (#1698)

2025-11-19 11:19:48 +01:00

rtc

[RTC] Real Time Chunking for Pi0, Smolvla, Pi0.5 (#1698)

2025-11-19 11:19:48 +01:00

smolvla

[RTC] Real Time Chunking for Pi0, Smolvla, Pi0.5 (#1698)

2025-11-19 11:19:48 +01:00

wall_x

Fix invalid syntax (#2752)

2026-01-05 12:13:42 +01:00

xvla

feat(policies): Add X-VLA (#2405)

2025-12-03 15:29:14 +01:00

test_policies.py

feat(sim): add metaworld env (#2088)

2025-10-14 17:21:18 +02:00

test_sac_config.py

chore: remove unused code (#2062)

2025-09-29 10:49:36 +02:00

test_sac_policy.py

fix(sac): make temperature a property to fix checkpoint resume bug (#2877)

2026-01-30 12:23:22 +01:00

test_sarm_processor.py

Add sarm (#2639)

2025-12-18 12:50:32 +01:00

test_sarm_subtask_annotations.py

Add sarm (#2639)

2025-12-18 12:50:32 +01:00

test_sarm_utils.py

Add sarm (#2639)

2025-12-18 12:50:32 +01:00