emailweixu
emailweixu
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_utils.add_variables_summaries` cannot generate summary for all the weights.
I tried to run the code for Atari Freeway using the following command with the default settings in the code: ```bash python main.py --env FreewayNoFrameskip-v4 \ --case atari \ --opr...
Examples in xrobot/python_examples directory needs extra files whose paths are hard coded. Are there any examples which I can run directly?
### Describe the bug When the function is called with num_samples=1, the expected result is [int(time_horizon/time_interval)] However, the result is off by 1: [int(time_horizon/time_interval)+1] This can be verified by the...
According to the code (https://github.com/openai/phasic-policy-gradient/blob/master/phasic_policy_gradient/train.py#L14), arch 'detach' seems corresponding to the single-network variant described in section 3.6 of the paper. According the paper and the comment in the code, the...
The speedup is great! Thanks for sharing this. Do you have plan to support training? Wei
**Describe the bug** When a dataclass is instantiated using keyword arguments, the non-existing keyword is not being report as error. This gives the user the erroneous sense that all the...
**Concisely describe the proposed feature** I was implementing a hashing function in taichi scope. Naturally, the hash function involves some multiplications and bit shift operations, which cause a lot of...
**Describe the bug** It seems that taichi complains about the return type. **To Reproduce** Please post a **minimal sample code** to reproduce the bug. The developer team will put a...