Add TorchRL to the Notable Related Libraries in README.md (#60)

Co-authored-by: Mark Towers <[email protected]>

README.md

@@ -53,6 +53,7 @@ Please note that this is an incomplete list, and just includes libraries that th
 
 * [CleanRL](https://github.com/vwxyzjn/cleanrl) is a learning library based on the Gym API. It is designed to cater to newer people in the field and provides very good reference implementations.
 * [Tianshou](https://github.com/thu-ml/tianshou) is a learning library that's geared towards very experienced users and is design to allow for ease in complex algorithm modifications.
+* [TorchRL](https://github.com/pytorch/rl) is the pytorch domain library for RL. It is fully compatible with the Gym API. It provides reusable building blocks for RL algorithms. It supports single and multi-agent, single and multi-tasks, distributed learning and many more features.
 * [RLlib](https://docs.ray.io/en/latest/rllib/index.html) is a learning library that allows for distributed training and inferencing and supports an extraordinarily large number of features throughout the reinforcement learning space.
 * [PettingZoo](https://github.com/Farama-Foundation/PettingZoo) is like Gym, but for environments with multiple agents.