| About the reinforcement-learning category |      | 7 | 4439 | October 18, 2023 |
| Implementation of Hierarchical Actor Critic with PPolicy-on Policy-off Policy Optimization for primitive actions |  | 0 | 7 | October 15, 2025 |
| Model Boilerplate for a Simple DQN |  | 0 | 11 | October 11, 2025 |
| PyTorch Compatibility with Older CUDA Versions |   | 1 | 32 | September 20, 2025 |
| Agent Masking in Multi-agent environment? |  | 0 | 20 | September 7, 2025 |
| Batching a multicategorical spec |   | 4 | 80 | August 27, 2025 |
| How to pass options to env.reset within a data collector | | 0 | 20 | August 26, 2025 |
| Environments from scratch with Torchrl |  | 17 | 1327 | August 25, 2025 |
| How to manage done in a batched custom Env? | | 3 | 50 | August 25, 2025 |
| ClipPPOLoss problem with MaskedCategorical dist |  | 2 | 38 | August 21, 2025 |
| CosTrader Env from scratch... and transform problem | | 3 | 31 | August 15, 2025 |
| PPO with Categorical Action... help | | 10 | 92 | August 14, 2025 |
| Question about TorchRL ParallelEnv error on single-gpu device |  | 3 | 51 | August 5, 2025 |
| Help understanding data collectors | | 1 | 48 | August 4, 2025 |
| Should we split the trajectories prior to calculating the loss for a DQN? | | 1 | 28 | August 4, 2025 |
| Question About If PPO Training Will Work |  | 1 | 61 | July 29, 2025 |
| RTX 5090 interconnection with pytorch |  | 6 | 168 | July 28, 2025 |
| Model almost instantly produces "nan" |  | 4 | 140 | July 19, 2025 |
| What loss function should the inner loop of MAML use? |    | 2 | 84 | June 27, 2025 |
| TruncatedNormal loc argument |  | 3 | 49 | June 19, 2025 |
| Using buffers in ParallelEnvs / MultiSyncCollectors |  | 2 | 124 | June 16, 2025 |
| Multi-agent RL with different agent action spaces |  | 0 | 51 | June 12, 2025 |
| Policy Gradient For Pong Not Learning |  | 0 | 27 | May 28, 2025 |
| Torchrl kl_div for old and new policy |  | 0 | 40 | April 7, 2025 |
| Custom Vectorized environment for torchrl | | 3 | 119 | April 3, 2025 |
| Gymnasium FrozenLake - why one-hot encoding for state is required? |  | 0 | 61 | March 27, 2025 |
| Training Machine Learning Model In Browser For Reinforcement Learning | | 0 | 74 | March 20, 2025 |
| Defining a ProbalisticActor with two normal distributions |   | 17 | 166 | March 13, 2025 |
| Feature Request: Add a `torch.range_map` operator for easy value range mapping |  | 1 | 50 | March 3, 2025 |
| TorchRL cpu-only installation |  | 4 | 305 | February 28, 2025 |