Giters
keiohta
/
tf2rl
TensorFlow2 Reinforcement Learning
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
460
Watchers:
18
Issues:
120
Forks:
103
keiohta/tf2rl Issues
AttributeError: module 'tensorflow' has no attribute 'version'
Closed
a year ago
Comments count
1
Possible error in critic update in SAC-AE algorithm
Updated
2 years ago
Comments count
2
Example of GAIFO for atari?
Updated
2 years ago
ModuleNotFoundError: No module named 'future'
Closed
2 years ago
Comments count
1
"TypeError: 'range' object cannot be interpreted as an integer" when attempting to use the __call__() method of IRLTrainer
Updated
2 years ago
Cannot run: run_apex_ddpg.py
Closed
2 years ago
Comments count
2
DeprecatedEnv error for Pendulum-v0
Closed
2 years ago
Comments count
1
Improve document
Updated
3 years ago
Discount not applied in evaluate_policy?
Closed
3 years ago
Comments count
9
How to use multiple GPU to train
Closed
3 years ago
Comments count
2
How to save the model and after the train of policy, how to use the policy on the new environment?
Closed
3 years ago
Comments count
1
Slow sampling from expert dataset in IRL traning loop
Closed
3 years ago
Comments count
6
problem with load_trajectories function in experiments/utils.py
Closed
3 years ago
Comments count
3
Unused argument `max_steps' in the function restore_latest_n_traj
Closed
3 years ago
Setting step size in trainer.py for evaluate policy
Closed
3 years ago
Comments count
2
Wrapping For Absorbing State in case of off-policy GAIL/GAIfO/VAIL (DAC)
Closed
3 years ago
Fix categorical policy
Updated
3 years ago
Implement RAD
Updated
3 years ago
Fix atari-py related errors
Closed
3 years ago
Comments count
1
Implement SAC+AE
Closed
3 years ago
Add recent version of TensorFlow
Closed
3 years ago
Comments count
4
GAIfO doesn't work with Ant-v2.
Closed
3 years ago
Unset training-phase.
Updated
3 years ago
Comments count
2
how can I use pretrained model after training
Closed
3 years ago
Comments count
2
Implement CURL
Updated
3 years ago
Comments count
2
GAIL could not work on Hopper-v2
Closed
4 years ago
Comments count
10
Bug: example/run_apex_dqn.py
Closed
3 years ago
Problems at GitHub Actions
Closed
3 years ago
The apex implementation seems quite slow
Updated
3 years ago
Comments count
4
Container Support
Closed
4 years ago
Comments count
3
TFP version incompatibility
Closed
4 years ago
Feature Request: Document Site for TF2RL
Closed
4 years ago
Comments count
1
FeatureRequest: Trainer without argparse
Closed
4 years ago
Reward nan
Closed
4 years ago
Comments count
15
GAIL could not work on Pendulum-v0
Closed
4 years ago
Comments count
6
Inconsistency DDPG and SAC
Closed
4 years ago
[Feature Request] Linter on GitHub Actions
Closed
4 years ago
Multi-platform Unit Test
Closed
4 years ago
dose the code support MPI to speed up the training?
Closed
4 years ago
Comments count
4
pixel obs
Closed
4 years ago
Comments count
5
A lot of warning for tf.function retracing
Updated
4 years ago
Support tf2.1
Closed
4 years ago
Comments count
2
Performance of PPO to 'PongNoFrameskip-v4'
Closed
4 years ago
Comments count
4
Where is mpc_trainer.py used in tf2rl?
Closed
4 years ago
Comments count
5
SAC_Discrete does not learn for Acrobot v1
Closed
4 years ago
Comments count
4
suggestion
Closed
4 years ago
Comments count
1
Illegal instruction (core dumped)
Closed
4 years ago
Comments count
7
Unable to find any devices for spec /device:GPU:0 [Op:__inference__train_body_2028]
Closed
4 years ago
Comments count
4
Implement CEM: Cross Entropy Method
Updated
4 years ago
TD3 IndentationError/OperatorNotAllowedInGraphError
Closed
4 years ago
Comments count
10
Previous
Next