sample-factory
sample-factory copied to clipboard
alex-petrenko
High throughput synchronous and asynchronous reinforcement learning
Integration and documentation with quad-swarm-rl. - fixed video generation by ignoring frames that are none and making a copy of frames for when the env reuses the same object to...
Initial implementation of an automatic model builder. Adds a default mode, which will generate encoder(s) automatically based on the shape(s) of the input observation(s). Adds a decoder option after the...
@edbeeching I will leave this here so we don't forget. Notes: - cpu_affinity() returns only half of the cores (40 instead of 80) which leads to workers only using 50%...
Good results on Atari is a must for any popular RL framework. Scope of this work: 1) Create `train_atari.py` and `enjoy_atari.py` scripts similar to `train_vizdoom` or `train_isaacgym` that would register...
The env info caching should be improved too. First of all, we need to figure out env info before we can create any of the actual sf2 processes because we...
I am trying to figure out how I could run quick evals during training. I saw an old issue about creating an eval worker using the current infrastructure, but that...
* Make sure we have an example folder and we can run 6 standard Mujoco environments * Try to match results from OpenRLBenchmark in terms of sample efficiency * Try...
Hi, Let's say we have a bunch of features (> 100) and the model is trained and working (but took forever to train). Is there a way to tell which...
Is there a way to restrict sample-factory to only use a subset of the CPUs on the machine instead of splitting them all amongst the number of workers? Thanks!
Metadata
Owner
Metadata
High throughput synchronous and asynchronous reinforcement learning