-
- [x] Foreword (2nd Edition): RL
- [x] Preface: RL
- [x] 1 Introduction: RL, JM, JN
- [x] 2 Geographic data in R: RL
- [x] 3 Attribute data operations: RL
- [x] 4 Spatial data operations: RL
- […
-
https://github.com/Alescontrela/AMP_for_hardware/blob/bfb0dbdcf32bdf83a916790bddf193fffc7e79b8/rsl_rl/rsl_rl/algorithms/amp_ppo.py#L235
When using state normalization, the `sample_amp_expert` tuple…
-
Current algorithm being used is DQN, or more specifically: DDQN. This off-policy algorithm is capable of adapting to the environment during episodes. However, this feature is not necessary for this pr…
-
* ACO (heuristic-based swarm algorithms)
* ACO_LS (our approach)
* OR-Tools (serve as ground truth, but should be considered as base line)
* RL (L2D, Jsp-env etc) reinforcement learning based algor…
-
Hi all,
I want to apply reinforcement learning using multi agent, specifically algorithms are PPO, TRPO, DDPG and A2C. I don't understand how to write Carla environment for these algorithm. Is any …
-
Hi, first of all, great work. This is a very useful library for research on RL and NLP. It will be very helpful if it's possible to add off-policy RL methods like Q-learning, SAC, etc. along with benc…
Div99 updated
3 months ago
-
Hi there!
Thank you for developing SBX! I'm currently working with SB3 for real-time robot control and was wondering if SBX supports the `framestack` using `DummyVecEnv` wrapper? Additionally, can …
-
Implement the best practices from multi-agent Rl community and stablebaselines3 into our algorithm. Further analyse similarities between petting zoo multi-agent implementation to current RL implementa…
-
Our algorithm has a long gradient chain, and the speedup is very obvious with jax in RL, and I would like to ask if using jax in GPUDrive would be much faster than torch? (after using jax.jit())
-
### What happened + What you expected to happen
Running the example script `rllib/examples/connectors/flatten_observations_dict_space.py` raises an error because the order of Connectors in the `env_t…