Publish Pusher-v5 medium-only policy

Publish Swimmer-v5 medium-only policy

Remove premature W&B link from model card

docs: ship the PolyForm Noncommercial 1.0.0 text in the repo

Update HumanoidStandup-v5 to pc4 320k

Unify KV sweep Trend column formatting

Add humanoidstandup-v5 to the root bundle manifest

Collapse detailed KV retention interpretation

Format KV sweep notes by environment

Align KV sweep narrative with normalized scores

Update HumanoidStandup pc4 200k scores

Update HumanoidStandup-v5 to pc4 200k bundle

Normalize KV retention sweep scores

Simplify Supported Environments table

Further shrink HumanoidStandup labels in model card

Shrink HumanoidStandup bundle label in model card

Add HumanoidStandup-v5 pc4 bundle

docs(card): refresh Ant-v5 to shipped bundle 30

Replace Ant-v5 model with validated bundle 30

Clean up Ant guidance and refresh reproduction runtime

Replace Walker2d-v5 with stable bundle 25

Align Hopper-v5 card text with refreshed sweep

Replace Hopper-v5 with stable bundle 24

Replace Ant-v5 with bundle 21 and refresh context sweep

Update Ant-v5 to v0.14.0 checkpoint

Add Trend column to KV cache retention sweep table

Add KV cache retention sweep (kv_cache_max_len 0.5x/1x/2x) to model card

Add Simple Ref. column to the supported-environments table

Update Ant-v5 bundle (50ep eval: 2835.61 -> 5262.53; norm 43.09 -> 79.08; runtime 0.12.0)

Re-measure all envs on the Minari dataset-native runtime (mujoco 3.2.3)

Update Humanoid-v5 bundle (50ep eval: 7718.75 -> 7842.01; falls 2/50 -> 1/50; runtime 0.12.0)

Update Humanoid-v5 bundle (50ep eval: 7255.03 -> 7718.75; falls 5/50 -> 2/50; runtime 0.12.0)

Refresh Humanoid-v5 score on current eval runtime (7255.03)

Update Humanoid-v5 bundle (50ep eval: mean 6456.56 -> 6838.38; runtime 0.11.0)

Document Humanoid-v5 refresh runtime

Update Humanoid-v5 bundle (50ep eval: mean 6259.01 -> 6456.56; runtime 0.11.0)

Update Humanoid-v5 bundle (50ep eval: mean 6511.87 -> 6259.01; runtime 0.11.0)

Migrate bundles to v2 (embedded state normalization, no sidecar)

Update HalfCheetah policy bundle

Update Humanoid-v5 eval scores (50ep mean 6511.87)

Update Humanoid-v5 policy bundle (50ep mean 6511.87)

Replace HalfCheetah-v5 policy bundle

Sync README: clarify autoregressive structure, move license to footer

Sync README: clarify autoregressive structure, move license to footer

Sync README: clarify autoregressive structure, move license to footer

Fix HalfCheetah-v5 package metadata

Add Hopper-v5 normalized scores

Document Hopper-v5 policy bundle

Add Hopper-v5 policy bundle

Document expert-free training data