google-deepmind / hanabi-learning-environment

hanabi_learning_environment is a research platform for Hanabi experiments.

google-deepmind/hanabi-learning-environment Issues

module 'tensorflow' has no attribute 'contrib'
Updated 2 years ago
windows OS pip install failed error C2039: "accumulate": not a member of "std"
Updated 2 years ago2
HanabiState.copy() truncates fireworks
Updated 2 years ago2
Defining Non-canonical (Float) Observations
Updated 2 years ago
Are there any scripts available to easily reproduce the results of the paper?
Updated 3 years ago2
Confusion on Observation Bit-Strings
Updated 3 years ago
[pyhanabi.py] HanabiState.copy() does not return correct fireworks
Closed 3 years ago2
Score at final state might be calculated wrong
Closed 3 years ago1
pip install error
Closed 4 years ago1
Visual studio 2019 is not recognised
Updated 4 years ago1
Support to multiple GPU training?
Updated 4 years ago
PyPI Release
Updated 4 years ago2
Error in Pip install
Updated 4 years ago1
Question: Why no observation stacking?
Closed 5 years ago1
[Feature Request] Start game from specific state
Updated 4 years ago1
rl_env.step() exits the program if illegal move is passed instead of throwing an exception
Updated 5 years ago1
checkpointer._clean_up_old_checkpoints not working as intended/documented?
Updated 5 years ago
observation stacking?
Closed 5 years ago2
Interoperable game record format / export / import
Updated 5 years ago
ACHA agent?
Closed 5 years ago4
UnicodeDecodeError when attempting to load checkpoint
Closed 5 years ago2
API documentation
Updated 5 years ago5
Ad-Hoc Play
Closed 5 years ago
Error running /usr/bin/ranlib: vfork
Closed 5 years ago2
Mac OS - lib failing to load
Closed 5 years ago5
Error when trying to access certain card_knowledge functions
Closed 5 years ago1
Issues running agents/rainbow/run_experiment.py (import fails and agent does not improve)
Updated 5 years ago4
Coding style
Closed 5 years ago1
Error compiling
Closed 5 years ago