File tree Expand file tree Collapse file tree 5 files changed +70
-0
lines changed
nemo_rl/environments/simulated_user Expand file tree Collapse file tree 5 files changed +70
-0
lines changed Original file line number Diff line number Diff line change 1+ # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
2+ #
3+ # Licensed under the Apache License, Version 2.0 (the "License");
4+ # you may not use this file except in compliance with the License.
5+ # You may obtain a copy of the License at
6+ #
7+ # http://www.apache.org/licenses/LICENSE-2.0
8+ #
9+ # Unless required by applicable law or agreed to in writing, software
10+ # distributed under the License is distributed on an "AS IS" BASIS,
11+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+ # See the License for the specific language governing permissions and
13+ # limitations under the License.
14+
115"""Run GRPO with the Unique Numbers Simulator using ADK.
216
317This script sets up and executes the Group Relative Policy Optimization (GRPO) algorithm
Original file line number Diff line number Diff line change 1+ # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
2+ #
3+ # Licensed under the Apache License, Version 2.0 (the "License");
4+ # you may not use this file except in compliance with the License.
5+ # You may obtain a copy of the License at
6+ #
7+ # http://www.apache.org/licenses/LICENSE-2.0
8+ #
9+ # Unless required by applicable law or agreed to in writing, software
10+ # distributed under the License is distributed on an "AS IS" BASIS,
11+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+ # See the License for the specific language governing permissions and
13+ # limitations under the License.
14+
115import asyncio
216import logging
317import random
Original file line number Diff line number Diff line change 1+ # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
2+ #
3+ # Licensed under the Apache License, Version 2.0 (the "License");
4+ # you may not use this file except in compliance with the License.
5+ # You may obtain a copy of the License at
6+ #
7+ # http://www.apache.org/licenses/LICENSE-2.0
8+ #
9+ # Unless required by applicable law or agreed to in writing, software
10+ # distributed under the License is distributed on an "AS IS" BASIS,
11+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+ # See the License for the specific language governing permissions and
13+ # limitations under the License.
14+
115starting_user_prompt = (
216 "I will play a game with you. I have a list of integers in mind and can NOT tell you. "
317 "Your goal is to guess the count of UNIQUE numbers in my list. The only 2 things you can do is the following: "
Original file line number Diff line number Diff line change 1+ # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
2+ #
3+ # Licensed under the Apache License, Version 2.0 (the "License");
4+ # you may not use this file except in compliance with the License.
5+ # You may obtain a copy of the License at
6+ #
7+ # http://www.apache.org/licenses/LICENSE-2.0
8+ #
9+ # Unless required by applicable law or agreed to in writing, software
10+ # distributed under the License is distributed on an "AS IS" BASIS,
11+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+ # See the License for the specific language governing permissions and
13+ # limitations under the License.
14+
115"""Simulated user environment for counting unique numbers."""
216
317from __future__ import annotations
Original file line number Diff line number Diff line change 1+ # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
2+ #
3+ # Licensed under the Apache License, Version 2.0 (the "License");
4+ # you may not use this file except in compliance with the License.
5+ # You may obtain a copy of the License at
6+ #
7+ # http://www.apache.org/licenses/LICENSE-2.0
8+ #
9+ # Unless required by applicable law or agreed to in writing, software
10+ # distributed under the License is distributed on an "AS IS" BASIS,
11+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+ # See the License for the specific language governing permissions and
13+ # limitations under the License.
14+
115import asyncio
216import re
317import sys
You can’t perform that action at this time.
0 commit comments