MOBA_RL
MOBA_RL copied to clipboard
kimbring2
Deep Reinforcement Learning for Multiplayer Online Battle Arena
Hi I had a problem when I download dota2 client 5110. It shows 'zipping' forever, then 'failed to download'. I really appreciate if you could provide any advice.
After downloading and decompressing 'dota2_client_5110' into one folder, I put it the under '~/.local/share/Steam/steamapps/common' and change the path in __main__.py as below, > game_path = os.path.expanduser("~/.local/share/Steam/steamapps/common/dota2_client_5110/game") and set the path...
some problem about undefined symbol:_ZNK10tensorflow8OpKernel11TraceStringERKNS_15OpKernelContextEb
when I run the python learner_1.py --workspace_path [your path]/dr-derks-mutant-battlegrounds/ I meet some problems like this : tensorflow.python.framework.errors_impl.NotFoundError: /home/public/grpc/python/../grpc_cc.so: undefined symbol: _ZNK10tensorflow8OpKernel11TraceStringERKNS_15OpKernelContextEb
Hello Kim, We here at STRATZ would love to take this project further if your interested. Please contact me at ken at stratz dot com. We can help provide resources...
Good job! Did you complete this project on your own? I believe that converting this into a self-play zero-sum game would yield excellent results. and remove derk.
Hello! Our static bug checker has found a performance issue in dota2/omninight/learner_dota.py: [`create_host`](https://github.com/kimbring2/MOBA_RL/blob/f3a02142e9125ee959eedd792b52d64545f5a3a5/dota2/omninight/learner_dota.py#L579) is repeatedly called in a for loop, but there are tf.function decorated functions [`inference`](https://github.com/kimbring2/MOBA_RL/blob/f3a02142e9125ee959eedd792b52d64545f5a3a5/dota2/omninight/learner_dota.py#L492) and [`agent_inference`](https://github.com/kimbring2/MOBA_RL/blob/f3a02142e9125ee959eedd792b52d64545f5a3a5/dota2/omninight/learner_dota.py#L543) defined...
Thank you for sharing of your work! I am very interested in the dota2-replay-parser section of this repo. But I met some problem when running the replay-parser code at this...
