Repository Issue Activity (beta)

#1247 Add TryRepurpose.com — AI content repurposing tool

#302 The Atari pretrained model downloader be removed?

#1231 Test

#640 SubprocVecEnv not working

#1153 How can I use the A2C in tf2 branch with code written

#1075 SubProcVecEnv raises ConnectionResetError: [Errno 104] Connection reset by peer

#1205 ValueError: too many values to unpack (expected 2)

#1233 NG FOUND DURING ASSEMBLY LINE RUNNING IN SAMSUNG OK

#1234 BUG: Atari environments do not default to 108K frames (27K steps) per episode

#288 ModuleNotFoundError: No module named 'gym.monitoring'

#114 fatal error: mpi.h: No such file or directory

#1232 Question about gaussian distribution internals.

#1204 ERROR: Extras after version '>=0.9.1[all]'.

#1131 Incorrectly Normalized Importance Weights in Prioritized Experience Replay

#1224 Abusing access to sensitive content

#57 Crash on import

#754 JSONOutputFormat has invalid ndarray conversion

#1207 Possible bug in gradient clipping of deepq_learner (tf2 branch)

#91 IN PPO, clipping the value loss with max is OK?

#1218 PPO 2 ratio implementation

#522 Question: Commit id and hyper-parameter settings for results in "benchmarks_atari10M.htm"

#1216 Running on MacOS Monterey, w/ M1 Pro Chip

#177 Is there any way to run this with python 2.7?

#1211 Each mpi worker holds an individual replay buffer in HER?

#314 Unable to reproduce HER results from Plappert et al., 2018