MillionIntegrals/vel issues and pull requests

#75 - Bump certifi from 2019.3.9 to 2022.12.7

Pull Request - State: open - Opened by dependabot[bot] about 2 years ago
Labels: dependencies

#74 - Bump pillow from 6.2.0 to 9.3.0

Pull Request - State: open - Opened by dependabot[bot] about 2 years ago
Labels: dependencies

#73 - Bump ujson from 1.35 to 5.4.0

Pull Request - State: open - Opened by dependabot[bot] over 2 years ago
Labels: dependencies

#72 - Bump numpy from 1.16.2 to 1.22.0

Pull Request - State: open - Opened by dependabot[bot] over 2 years ago
Labels: dependencies

#71 - Bump ujson from 1.35 to 5.2.0

Pull Request - State: closed - Opened by dependabot[bot] over 2 years ago - 1 comment
Labels: dependencies

#70 - Bump pillow from 6.2.0 to 9.0.1

Pull Request - State: closed - Opened by dependabot[bot] almost 3 years ago - 1 comment
Labels: dependencies

#69 - Bump pillow from 6.2.0 to 9.0.0

Pull Request - State: closed - Opened by dependabot[bot] about 3 years ago - 1 comment
Labels: dependencies

#68 - Bump opencv-python from 4.0.0.21 to 4.2.0.32

Pull Request - State: open - Opened by dependabot[bot] over 3 years ago
Labels: dependencies

#67 - Bump opencv-python from 4.0.0.21 to 4.1.1.26

Pull Request - State: closed - Opened by dependabot[bot] over 3 years ago - 1 comment
Labels: dependencies

#66 - Bump pillow from 6.2.0 to 8.3.2

Pull Request - State: closed - Opened by dependabot[bot] over 3 years ago - 1 comment
Labels: dependencies

#65 - Bump pillow from 6.2.0 to 8.2.0

Pull Request - State: closed - Opened by dependabot[bot] over 3 years ago - 1 comment
Labels: dependencies

#64 - Bump urllib3 from 1.24.2 to 1.26.5

Pull Request - State: open - Opened by dependabot[bot] over 3 years ago
Labels: dependencies

#63 - Bump py from 1.8.0 to 1.10.0

Pull Request - State: open - Opened by dependabot[bot] almost 4 years ago
Labels: dependencies

#62 - Bump pygments from 2.3.1 to 2.7.4

Pull Request - State: open - Opened by dependabot[bot] almost 4 years ago
Labels: dependencies

#61 - Bump pyyaml from 5.1 to 5.4

Pull Request - State: open - Opened by dependabot[bot] almost 4 years ago
Labels: dependencies

#60 - Bump pillow from 6.2.0 to 8.1.1

Pull Request - State: closed - Opened by dependabot[bot] almost 4 years ago - 1 comment
Labels: dependencies

#59 - Bump bleach from 3.1.0 to 3.3.0

Pull Request - State: open - Opened by dependabot[bot] about 4 years ago
Labels: dependencies

#58 - Bump bleach from 3.1.0 to 3.1.4

Pull Request - State: closed - Opened by dependabot[bot] almost 5 years ago - 1 comment
Labels: dependencies

#57 - Bump bleach from 3.1.0 to 3.1.2

Pull Request - State: closed - Opened by dependabot[bot] almost 5 years ago - 1 comment
Labels: dependencies

#56 - Bump bleach from 3.1.0 to 3.1.1

Pull Request - State: closed - Opened by dependabot[bot] almost 5 years ago - 1 comment
Labels: dependencies

#55 - Minor fixes to rl.command.record_movie_command and evaluate

Pull Request - State: closed - Opened by matrig about 5 years ago

#54 - Bump pillow from 5.4.1 to 6.2.0

Pull Request - State: closed - Opened by dependabot[bot] over 5 years ago
Labels: dependencies

#53 - Multiple optimizers support

Issue - State: closed - Opened by galatolofederico over 5 years ago - 6 comments

#52 - Configurable Evaluator cache

Pull Request - State: closed - Opened by galatolofederico over 5 years ago - 2 comments

#51 - Create documentation with something like portay.

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

#50 - Name error in stochastic_policy_rnn_model.py

Issue - State: closed - Opened by yangysc over 5 years ago - 1 comment

#49 - What's the reason behind using orthogonal weight initialization?

Issue - State: closed - Opened by phizaz over 5 years ago - 1 comment

#48 - What is consideration regarding "FIRE" action in the env?

Issue - State: closed - Opened by phizaz over 5 years ago - 6 comments

#47 - How do models deal with environments with no scale_float_frames?

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

#46 - How can I cite you?

Issue - State: closed - Opened by phizaz over 5 years ago - 2 comments

#45 - Compatibility of DQN and parallel environments

Issue - State: closed - Opened by maxwab almost 6 years ago - 5 comments

#44 - Candidate v0.4

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

#43 - Rename models to policies

Issue - State: closed - Opened by MillionIntegrals almost 6 years ago - 1 comment
Labels: code-quality

#42 - Include linter in the build process

Issue - State: closed - Opened by MillionIntegrals almost 6 years ago - 1 comment
Labels: code-quality

#41 - Soft Actor-Critic and Twin Delayed DDPG

Issue - State: open - Opened by MillionIntegrals almost 6 years ago
Labels: new-model

#40 - Implement Transformer network architecture

Issue - State: open - Opened by MillionIntegrals almost 6 years ago
Labels: new-model

#39 - Variational Auto-Encoder

Issue - State: closed - Opened by MillionIntegrals almost 6 years ago - 1 comment
Labels: new-model

#38 - [v0.3] Record command getting Type exception using NormalizeObservations

Issue - State: closed - Opened by joecargill almost 6 years ago - 2 comments

#37 - Loading saved models?

Issue - State: closed - Opened by sgillen about 6 years ago - 2 comments
Labels: question

#36 - PyTorch 1.0 support

Issue - State: closed - Opened by grozail about 6 years ago - 2 comments
Labels: enhancement

#35 - Understanding results from the ACER algorithm on Enduro

Issue - State: closed - Opened by yngtodd about 6 years ago - 3 comments

#34 - Merge .api and .api.base packages

Issue - State: closed - Opened by MillionIntegrals about 6 years ago - 1 comment
Labels: enhancement

#33 - Factor out input_block from each model

Issue - State: closed - Opened by MillionIntegrals about 6 years ago - 1 comment
Labels: enhancement

#32 - Unify LSTM, GRU and RNN models

Issue - State: closed - Opened by MillionIntegrals about 6 years ago - 1 comment
Labels: enhancement

#31 - Large refactoring of envs, vec envs, environment rollers and frame stack

Issue - State: closed - Opened by MillionIntegrals about 6 years ago - 1 comment
Labels: enhancement

#30 - Can't run YAML config file in local directory

Issue - State: closed - Opened by maximecb about 6 years ago - 18 comments
Labels: question

#29 - Minimize unnecessary dependencies when installing

Issue - State: closed - Opened by maximecb about 6 years ago - 7 comments

#28 - Add breakout dqn example

Pull Request - State: closed - Opened by yngtodd about 6 years ago - 7 comments

#27 - [WIP] Qbert PPO example script

Pull Request - State: closed - Opened by yngtodd over 6 years ago - 3 comments

#26 - Yaml

Pull Request - State: closed - Opened by yngtodd over 6 years ago - 1 comment

#25 - Viewing results.

Issue - State: closed - Opened by yngtodd over 6 years ago - 13 comments
Labels: question

#24 - fix: minor bug

Pull Request - State: closed - Opened by youngbink over 6 years ago - 1 comment

#23 - Add support for LSTM policies

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: enhancement

#22 - Undefined names: import os, uuid, pandas in monitor.py

Pull Request - State: closed - Opened by cclauss over 6 years ago - 1 comment

#21 - Implementation of Guided Policy Search

Issue - State: open - Opened by kabirahuja2431 over 6 years ago - 7 comments
Labels: new-model

#20 - Test launcher/dependency injection code

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#19 - Use torch.distributions instead of handrolled logic

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#18 - Implement 'Rainbow' DQN version.

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: new-model

#17 - Store config in the DB together with the metrics.

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#16 - Nicer API for progress idx and 'progress_meter'

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#15 - Add reset flag to the launcher

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#14 - Implement tracking percentiles (e.g. 90%, 10%) of episode rewards.

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#13 - Implement ENV wrapper for limiting episode length

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#12 - Add README information how to run a config

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: documentation

#11 - Callbacks should access data-dict before metrics

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#10 - Revive test-time augmentation

Issue - State: open - Opened by MillionIntegrals over 6 years ago
Labels: smaler-feature

#9 - Bug in visdom environment naming

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: bug

#8 - Training time measurements

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 2 comments
Labels: smaler-feature

#7 - Think about restarting reinforcement learning algorithms

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: speculative

#6 - Expose more checkpointing options to the model

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#5 - Parametrize visdom connection better

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#4 - Write output of LrFinder to storage rather than to matplotlib

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: smaler-feature

#3 - Super-convergence experiments

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: enhancement

#2 - Planet Earth transfer learning

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 1 comment
Labels: enhancement

#1 - Implement policy gradient reinforcement learning algorithms

Issue - State: closed - Opened by MillionIntegrals over 6 years ago - 7 comments
Labels: enhancement

GitHub / MillionIntegrals/vel issues and pull requests