amend links

pytorch · Apr 22, 2024 · 682c4f7 · 682c4f7
1 parent 967d6fa
commit 682c4f7
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 10 deletions.
diff --git a/tutorials/sphinx-tutorials/multiagent_competitive_ddpg.py b/tutorials/sphinx-tutorials/multiagent_competitive_ddpg.py
@@ -935,8 +935,8 @@ def process_batch(batch: TensorDictBase) -> TensorDictBase:
 # - How we can use :class:`tensordict.TensorDict` to carry multi-agent multi-group data;
 # - How we can tie all the library components (collectors, modules, replay buffers, and losses) in a multi-agent multi-group MADDPG/IDDPG training loop.
 #
-# Now that you are proficient with multi-agent DDPG, you can check out all
-# `TorchRL multi-agent examples <https://github.com/pytorch/rl/tree/main/sota-implementations/multiagent>`__.
+# Now that you are proficient with multi-agent DDPG, you can check out all the TorchRL multi-agent implementations in the
+# GitHub repository.
 # These are code-only scripts of many popular MARL sota-implementations such as the ones seen in this tutorial,
 # QMIX, MADDPG, IQL, and many more!
 #

diff --git a/tutorials/sphinx-tutorials/multiagent_ppo.py b/tutorials/sphinx-tutorials/multiagent_ppo.py
@@ -14,12 +14,8 @@
 This tutorial demonstrates how to use PyTorch and :py:mod:`torchrl` to
 solve a Multi-Agent Reinforcement Learning (MARL) problem.
 
-A code-only version of this tutorial is available in the
-`TorchRL examples <https://github.com/pytorch/rl/tree/main/sota-implementations/multiagent/mappo_ippo.py>`__,
-alongside other simple scripts for many MARL sota-implementations (QMIX, MADDPG, IQL).
-
-For ease of use, this tutorial will follow the general structure of the already available
-`single agent PPO tutorial <https://pytorch.org/rl/tutorials/coding_ppo.html>`__.
+For ease of use, this tutorial will follow the general structure of the already available in:
+:doc:`/tutorials/coding_ppo`.
 It is suggested but not mandatory to get familiar with that prior to starting this tutorial.
 
 In this tutorial, we will use the *Navigation* environment from
@@ -786,8 +782,8 @@
 # - How we can use :class:`tensordict.TensorDict` to carry multi-agent data;
 # - How we can tie all the library components (collectors, modules, replay buffers, and losses) in a multi-agent MAPPO/IPPO training loop.
 #
-# Now that you are proficient with multi-agent PPO, you can check out all
-# `TorchRL multi-agent examples <https://github.com/pytorch/rl/tree/main/sota-implementations/multiagent>`__.
+# Now that you are proficient with multi-agent DDPG, you can check out all the TorchRL multi-agent implementations in the
+# GitHub repository.
 # These are code-only scripts of many popular MARL sota-implementations such as the ones seen in this tutorial,
 # QMIX, MADDPG, IQL, and many more!
 #