Issues
- 1
- 2
Possible error in critic update in SAC-AE algorithm
#162 opened by Cerphilly - 0
Example of GAIFO for atari?
#161 opened by rrags - 1
ModuleNotFoundError: No module named 'future'
#160 opened by yuhe-Ray - 0
"TypeError: 'range' object cannot be interpreted as an integer" when attempting to use the __call__() method of IRLTrainer
#159 opened by peteris-racinskis - 2
Cannot run: run_apex_ddpg.py
#91 opened - 1
DeprecatedEnv error for Pendulum-v0
#154 opened by ymd-h - 0
Improve document
#152 opened by ymd-h - 9
Discount not applied in evaluate_policy?
#143 opened by naji-s - 2
How to use multiple GPU to train
#147 opened by hongjianjiang - 1
How to save the model and after the train of policy, how to use the policy on the new environment?
#149 opened by hongjianjiang - 6
Slow sampling from expert dataset in IRL traning loop
#126 opened by HesNobi - 3
- 0
- 2
Setting step size in trainer.py for evaluate policy
#142 opened by naji-s - 0
- 0
Fix categorical policy
#140 opened by keiohta - 0
Implement RAD
#139 opened by keiohta - 1
Fix atari-py related errors
#137 opened by keiohta - 0
Implement SAC+AE
#131 opened by keiohta - 4
Add recent version of TensorFlow
#135 opened by sff1019 - 0
GAIfO doesn't work with Ant-v2.
#127 opened by HesNobi - 2
Unset training-phase.
#125 opened by HesNobi - 2
how can I use pretrained model after training
#124 opened by l976308589 - 2
Implement CURL
#116 opened by keiohta - 10
GAIL could not work on Hopper-v2
#109 opened by zhihaocheng - 0
Bug: example/run_apex_dqn.py
#120 opened by ymd-h - 0
Problems at GitHub Actions
#118 opened by ymd-h - 4
The apex implementation seems quite slow
#117 opened by sorryformyself - 3
Container Support
#110 opened by ymd-h - 0
TFP version incompatibility
#112 opened by ymd-h - 1
Feature Request: Document Site for TF2RL
#106 opened by ymd-h - 0
FeatureRequest: Trainer without argparse
#104 opened by ymd-h - 15
Reward nan
#92 opened by haoyu-x - 6
GAIL could not work on Pendulum-v0
#103 opened by zhihaocheng - 0
Inconsistency DDPG and SAC
#94 opened by llewynS - 0
[Feature Request] Linter on GitHub Actions
#101 opened by ymd-h - 0
Multi-platform Unit Test
#96 opened by ymd-h - 4
- 5
- 0
A lot of warning for tf.function retracing
#99 opened by ymd-h - 2
Support tf2.1
#84 opened by keiohta - 4
Performance of PPO to 'PongNoFrameskip-v4'
#90 opened by Callmejp - 5
Where is mpc_trainer.py used in tf2rl?
#89 opened - 4
- 1
suggestion
#86 opened by zzchuman - 7
Illegal instruction (core dumped)
#87 opened by sfornengo - 4
Unable to find any devices for spec /device:GPU:0 [Op:__inference__train_body_2028]
#82 opened by tanjhysj0 - 0
Implement CEM: Cross Entropy Method
#85 opened by keiohta - 10