Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / numenta/nupic.embodied issues and pull requests
#67 - Extra experiments per journal review feedback
Pull Request -
State: closed - Opened by abhi-iyer almost 3 years ago
#66 - Changes to wandb arguments and requirements.txt
Pull Request -
State: closed - Opened by lucasosouza almost 3 years ago
#65 - Update paper_experiments.py
Pull Request -
State: closed - Opened by abhi-iyer almost 3 years ago
#64 - implements batchnorm and layernorm for MLPs
Pull Request -
State: open - Opened by lucasosouza almost 3 years ago
#63 - Notebook with latest analysis
Pull Request -
State: closed - Opened by lucasosouza almost 3 years ago
#62 - Readme for Multitask
Pull Request -
State: closed - Opened by lucasosouza almost 3 years ago
- 1 comment
#61 - Paper configs
Pull Request -
State: closed - Opened by abhi-iyer almost 3 years ago
#60 - Notebook for MTRL core results
Pull Request -
State: closed - Opened by karangrewal almost 3 years ago
- 1 comment
#59 - notebook to export data from wandb and other small changes
Pull Request -
State: closed - Opened by lucasosouza almost 3 years ago
- 1 comment
#58 - adds option to set seed for weight initialization
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
#57 - Reversing preprocessing linear layer bias change
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
- 1 comment
#56 - Fix to override weight initialization, making it mean centered
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
#55 - overrides weight initialization, removes bias in preprocessed layers
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
#54 - bug fixes and new debugging notebook
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
#53 - changes checkpoint frequency
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
#52 - Support for policy hooks for data visualization (single and composite), env updates in trainer, saving/restoring eval env state
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
- 2 comments
#51 - Visualizations
Pull Request -
State: closed - Opened by abhi-iyer about 3 years ago
- 1 comment
#50 - correct fix to restore flag
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
#49 - fix bug when not restoring
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
#48 - adds save and restore capabilities to trainer and algorithm
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
- 2 comments
#47 - Update multiseg_experiments.py
Pull Request -
State: closed - Opened by abhi-iyer about 3 years ago
#46 - Refactors policy/q-functions, pushes old code to deprecated, adds new optimizations/modular dendritic layers
Pull Request -
State: closed - Opened by abhi-iyer about 3 years ago
#45 - Refactors training loop, removes bidirectional message passing between trainer and algo
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
- 3 comments
#44 - FP16 training
Pull Request -
State: closed - Opened by abhi-iyer about 3 years ago
#43 - change eval frequency to 10
Pull Request -
State: closed - Opened by lucasosouza about 3 years ago
#42 - multitask: API refactoring , style changes to adhere to PEP8, local Ray GPU sampler
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#41 - Memory profiler
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
- 2 comments
#40 - Don't log model files while debugging
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#39 - Changes references from "robot-arm" to "disagreement", small fixes in np to tensor conversion
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#38 - Small fixes on model loading
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
- 1 comment
#37 - Reorganization into two frameworks, disagreement and multitask + small fixes to disagreement
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#36 - EOF and Segmentation Error after upgrading to python=3.8 and replacing baselines with stable_baselines
Issue -
State: open - Opened by lucasosouza over 3 years ago
- 2 comments
#35 - Changes to make it compatible with python 3.7
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#34 - Small changes after first test of the new implementation
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#33 - Refactoring of learn.py and Trainer class
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#32 - Makes auxiliary task independent of dynamic models
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#31 - Bug fixes for ppo update & backprob speed issue
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#30 - Small fixes and some comments and logging for debiggung speed issue
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#29 - Torchifies disagreement experiments
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#28 - Minor Logging fixes, Adding 2 new hyperparameter
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#27 - Code cleanup, refactor of the update function, and improvements to backprop through reward
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#26 - Initial draft of backprop through reward
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#25 - Implement gradient interference in MultiTask project
Issue -
State: closed - Opened by lucasosouza over 3 years ago
#24 - Change experiment names for SingleSegReLU1 and SingleSegReLU2
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
#23 - New experiment configs
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
#22 - Refactor Dendritic MLP and Policies/QFunctions to use nupic.research's dendritic mlp
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
#21 - Add MT50 runner script with MTSAC and different experiment configs for MT50.
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
#20 - Changes evaluation frequency
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#19 - Add Custom (MT)SAC files
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
#18 - Include network creation commits, fix min and max std bug for dendritic policy.
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
#17 - Create option to do PPO training on GPU.
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
#16 - change utils to garage utils
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
#15 - Minor changes in logging
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#15 - Minor changes in logging
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#14 - Model saving, loading & additional logging
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#13 - Code cleanup and improved readability
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#12 - Refactoring of DynamicsNet
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
- 1 comment
#11 - Small Fixes
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#10 - Garage vectorized sampler and other small edits.
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
#9 - First Draft - Learning with Disagreement
Pull Request -
State: closed - Opened by vkakerbeck over 3 years ago
#8 - First draft of exploration by disagreement pytorch reimplementation
Pull Request -
State: closed - Opened by lucasosouza over 3 years ago
#7 - Adds dendrite/sparse mlp models, modules, and policies, and integrates with garage.
Pull Request -
State: closed - Opened by akashvelu over 3 years ago
- 1 comment
#6 - fixes typo in requirements
Pull Request -
State: closed - Opened by lucasosouza almost 4 years ago
#5 - Updates to requirement.txt
Pull Request -
State: closed - Opened by lucasosouza almost 4 years ago
#4 - adds a unit test to WrapRobot as an example
Pull Request -
State: closed - Opened by lucasosouza almost 4 years ago
#3 - initial repo setup: style fixes for migrated code
Pull Request -
State: closed - Opened by lucasosouza almost 4 years ago
#2 - Proposed folders structure + migration of code from EIAI
Pull Request -
State: closed - Opened by lucasosouza almost 4 years ago
#1 - first commit, skeleton based on nupic.research
Pull Request -
State: closed - Opened by lucasosouza almost 4 years ago
- 4 comments