facebookresearch/deep_bisim4control issues and pull requests

#22 - reproducing the generalization results

Issue - State: open - Opened by sunchipsster1 over 1 year ago

#21 - Does the bisim loss influence the convergence of the forward and reward dynamics model?

Issue - State: open - Opened by chaobiubiu over 2 years ago

#20 - Transition Model Type "" behaves differently from "deterministic"

Issue - State: open - Opened by sebimarkgraf over 2 years ago

#19 - about baseline_agent

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

#18 - Questions about reproducing results

Issue - State: open - Opened by humanbins almost 3 years ago - 5 comments

#17 - Error!

Issue - State: open - Opened by lmc19970711 about 3 years ago

#16 - problems about the version of packages

Issue - State: open - Opened by ArronDZhang about 3 years ago

#15 - Hi, is there a way to run this with the simple distractors environments?

Issue - State: open - Opened by slerman12 about 3 years ago - 1 comment

#14 - Questions on reproducing CARLA

Issue - State: open - Opened by ttaa9 about 3 years ago - 1 comment

#13 - I don't understand a detail about the transition_reward_model loss function

Issue - State: open - Opened by TianQi-777 about 3 years ago - 1 comment

#12 - Questions about the default parameters

Issue - State: open - Opened by BillHan-Fantast about 3 years ago

#11 - Whether the reward model are applied in calculating J(Φ)

Issue - State: closed - Opened by indolentbear over 3 years ago

#10 - Question about augmentation

Issue - State: closed - Opened by tunglm2203 over 3 years ago - 1 comment

#9 - How to resume training

Issue - State: closed - Opened by tung-nd over 3 years ago

#8 - Cannot reproduce paper's results

Issue - State: closed - Opened by noobitard over 3 years ago - 5 comments

#7 - Conda environment file minor fix

Issue - State: closed - Opened by yanlai00 over 3 years ago - 1 comment

#6 - How many videos in the simple distractor experiments?

Issue - State: closed - Opened by kyonofx over 3 years ago - 1 comment

#5 - Reproducing the Generalization Experiments

Issue - State: closed - Opened by rraileanu over 3 years ago - 1 comment

#4 - Hyper-paramters for OpenAi's classic control environments

Issue - State: closed - Opened by bheijden over 3 years ago - 2 comments

#3 - Update train.py

Pull Request - State: closed - Opened by rowanmcallister over 3 years ago - 1 comment

#2 - Adding Code of Conduct file

Pull Request - State: closed - Opened by facebook-github-bot about 4 years ago
Labels: CLA Signed

#1 - Adding Contributing file