-
step = 5000: AverageReturn = 7.617593, AverageEpisodeLength = 21.000000
step = 10000: AverageReturn = 7.661649, AverageEpisodeLength = 21.049999
step = 15000: AverageReturn = 7.671409, AverageEpisod…
-
The dense layers created in mlp_layers have same names:
https://github.com/tensorflow/agents/blob/82317735484b99f8bcb6ec7cb99d1e73f058ca55/tf_agents/networks/utils.py#L172
Because of this, `eager_…
-
Hi,
I am trying to run train_eval_mushroom.py and get an attribute error in trainer.py:
AttributeError: module 'tf_agents.replay_buffers.replay_buffer' has no attribute 'BanditReplayBuffer'
A…
MHJYR updated
2 years ago
-
Installed dm-acme using the command `pip install dm-acme[envs,jax,tf] `
Running examples fails with a message that it can't import that package. I go into the python environment to view the actual …
-
Hello,
I'm trying to use a PPO tf-agent with a trained policy, but I get the following error
---------------------------------------------------------------------------
ValueError …
-
Here is a minimal example:
```python
from tf_agents.replay_buffers import tf_uniform_replay_buffer
import tensorflow as tf
batch_size = 8
counter = 0
data_spec = {'observations': tf.Tensor…
djl11 updated
4 years ago
-
I am trying to use TensorflowSharp with Unity ML Agents to produce a UWP build. However I am getting an error where it is unable to load libtensorflow.dll. Do you have a working sample using .NET Stan…
-
I have a DQN agent with policy of type to train a gym environment (CartPole-v1). I am using tf_agents 0.16.0 and gym 0.23.0
During saving the policy tf_agents.policies.policy_saver.PolicySaver I am …
-
```
RainbowAgent(sess=tensorflow.compat.v1.Session(),
num_actions=2,
stack_size=4,
observation…
-
# Bug Description
Hi, I am trying do multi-agent learning on large grid with different algorithm like SAC. All my changes are as followed:
(1)modify multiagent_traffic_light_grid.py (flow/examp…