openai/random-network-distillation issues and pull requests

#28 - how to install the 'exptag' package

Issue - State: open - Opened by jgp-github over 2 years ago

#27 - How to train agent with only intrinsic reward?

Issue - State: closed - Opened by zijGao over 2 years ago

#26 - Wrong PPO Model architecture.

Issue - State: open - Opened by alirezakazemipour about 4 years ago - 2 comments

#25 - updated the comments for better understanding

Pull Request - State: open - Opened by ProgrammerDG about 4 years ago

#24 - AttributeError: module 'baselines.logger' has no attribute 'ProfileKV'

Issue - State: open - Opened by fuxianh over 4 years ago - 1 comment

#23 - intrinsic reward and extrinsic reward

Issue - State: open - Opened by rainbow979 over 4 years ago - 2 comments

#22 - Problems while installing libraries required to run it [mpi4py]

Issue - State: open - Opened by TheRealRazbi over 4 years ago

#21 - module 'tensorflow_core._api.v2.nn' has no attribute 'rnn_cell'

Issue - State: closed - Opened by ArtificialIntelligenceRobot about 5 years ago

#20 - bug report: Type error

Issue - State: open - Opened by ThisIsIsaac about 5 years ago - 1 comment

#19 - Is 'news' in your code equivalent to 'dones' in OpenAI Gym?

Issue - State: closed - Opened by weak-orange-wind over 5 years ago

#18 - hard coded number of gpu's to 1 to make this run on macbook. https://…

Pull Request - State: closed - Opened by lhsu-cslt over 5 years ago

#17 - Samples of each epoch for optimization were not shuffled

Issue - State: open - Opened by boscotsang over 5 years ago

#16 - RewardForwardFilter to compute intrinsic returns for normalize intrinsic reward

Issue - State: open - Opened by boscotsang over 5 years ago - 2 comments

#15 - Fix typo in monitor.py

Pull Request - State: open - Opened by ajabri almost 6 years ago

#14 - RAM usage problem

Issue - State: closed - Opened by weak-orange-wind almost 6 years ago - 4 comments

#13 - why there are two calls to the policy, also where is the non intrinsic characteristic of intrinsic reward?

Issue - State: open - Opened by mehdimashayekhi almost 6 years ago - 1 comment

#12 - how to test?

Issue - State: closed - Opened by wangrui1996 almost 6 years ago - 1 comment

#11 - tf.stop_gradient missing?

Issue - State: closed - Opened by navneet-nmk almost 6 years ago - 3 comments

#10 - VecFrameStack class double

Issue - State: open - Opened by michael20at almost 6 years ago

#9 - Saving / Render

Issue - State: open - Opened by michael20at almost 6 years ago - 3 comments

#8 - update README with repo status

Pull Request - State: closed - Opened by christopherhesse almost 6 years ago

#7 - replay

Issue - State: open - Opened by TheCherry almost 6 years ago - 3 comments

#6 - requirement baseline / MuJoCo

Issue - State: closed - Opened by TheCherry almost 6 years ago - 1 comment

#5 - Enhancement

Pull Request - State: open - Opened by ss18 about 6 years ago

#4 - mpi_util 'RCALL_NUM_GPU' fix

Pull Request - State: closed - Opened by vpj about 6 years ago - 1 comment

#3 - Fix #1 KeyError: 'RCALL_NUM_GPU'

Pull Request - State: open - Opened by ei-grad about 6 years ago

#2 - Undefined names: Add missing imports in monitor.py

Pull Request - State: closed - Opened by cclauss about 6 years ago

#1 - KeyError: 'RCALL_NUM_GPU' ?

Issue - State: closed - Opened by lhlong about 6 years ago - 6 comments

Ecosyste.ms: Issues

GitHub / openai/random-network-distillation issues and pull requests