Resets recurrent state after episode termination in RSL-RL play.py (#3838)

# Description

This PR fixes an issue in recurrent policy evaluation where the
recurrent state was not being reset after an episode termination. The
missing reset caused residual memory to persist between episodes. The
fix ensures that `reset()` is now called during evaluation in `play.py`
for policy networks, including recurrent.

Fixes #3837  <!-- replace with actual issue number -->

## Type of change

- Bug fix (non-breaking change which fixes an issue)

## Screenshots

N/A

## Checklist

- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
`./isaaclab.sh --format`
- [ ] I have made corresponding changes to the documentation where
necessary
- [x] My changes generate no new warnings
- [x] I have added tests verifying that recurrent states are correctly
reset during evaluation
- [x] I have updated the changelog and corresponding version in the
extension’s `config/extension.toml` file
- [x] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there

Author: bikcrum

scripts/reinforcement_learning/rsl_rl/play.py

@@ -185,7 +185,9 @@ def main(env_cfg: ManagerBasedRLEnvCfg | DirectRLEnvCfg | DirectMARLEnvCfg, agen
             # agent stepping
             actions = policy(obs)
             # env stepping
-            obs, _, _, _ = env.step(actions)
+            obs, _, dones, _ = env.step(actions)
+            # reset recurrent states for episodes that have terminated
+            policy_nn.reset(dones)
         if args_cli.video:
             timestep += 1
             # Exit the play loop after recording one video

source/isaaclab/config/extension.toml

@@ -1,7 +1,7 @@
 [package]
 
 # Note: Semantic Versioning is used: https://semver.org/
-version = "0.47.5"
+version = "0.47.6"
 
 # Description
 title = "Isaac Lab framework for Robot Learning"

source/isaaclab/docs/CHANGELOG.rst

@@ -1,6 +1,16 @@
 Changelog
 ---------
 
+
+0.47.6 (2025-11-01)
+~~~~~~~~~~~~~~~~~~~~
+
+Fixed
+^^^^^
+
+* Fixed an issue in recurrent policy evaluation in RSL-RL framework where the recurrent state was not reset after an episode termination.
+
+
 0.47.5 (2025-10-30)
 ~~~~~~~~~~~~~~~~~~~