Ecosyste.ms: OpenCollective

An open API service for software projects hosted on Open Collective.

github.com/JuliaReinforcementLearning/ReinforcementLearning.jl

A reinforcement learning package for Julia
https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl

CompatHelper: bump compat for CUDA to 5 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for DomainSets to 0.7 for package ReinforcementLearningBase, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
Fix and refactor SAC

HenriDeh opened this pull request over 1 year ago
CompatHelper: bump compat for DomainSets to 0.7 for package ReinforcementLearningBase, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
An error

zsz00 opened this issue over 1 year ago
experiments failed

Yue-Wang-qvp opened this issue over 1 year ago
Nfq refactor

CasBex opened this pull request over 1 year ago
CompatHelper: bump compat for CUDA to 5 for package ReinforcementLearningZoo, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for CUDA to 5 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningExperiments, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for ReinforcementLearningZoo to 0.8 for package ReinforcementLearningExperiments, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningZoo, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
Prioritised DQN GPU

CasBex opened this pull request over 1 year ago
Prioritised DQN failing on GPU

CasBex opened this issue over 1 year ago
add retrace

HenriDeh opened this pull request over 1 year ago
Prioritized DQN experiment nonfunctional

CasBex opened this issue over 1 year ago
Fixing SAC Policy

gggoes opened this issue over 1 year ago
CompatHelper: bump compat for GPUArrays to 9 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
Fix multi thread env state in case N=1

johannes-fischer opened this pull request over 1 year ago
AssertionError: action in env.action_space

ZdM87 opened this issue over 1 year ago
TargetNetwork

HenriDeh opened this pull request over 1 year ago
Can implement this ARZ algorithm ?

zsz00 opened this issue over 1 year ago
CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningExperiments, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningZoo, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
Missing features in RLCore

HenriDeh opened this issue over 1 year ago
Spin off core packages

jeremiahpslewis opened this issue over 1 year ago
type Experiment

HenriDeh opened this pull request over 1 year ago
update docs to loop refactor

HenriDeh opened this pull request over 1 year ago
Improving Collaboration: Separate out the environment interface

zsunberg opened this issue over 1 year ago
Fix TotalRewardPerEpisode bug

jeremiahpslewis opened this pull request over 1 year ago
Refactor TRPO and VPG with EpisodesSampler

HenriDeh opened this pull request over 1 year ago
TD3 Policy unable to handle environments with multidimensional action spaces

gggoes opened this issue over 1 year ago
Bump RLCore version

jeremiahpslewis opened this pull request over 1 year ago
gpu updates RLExperiments, RLZoo

jeremiahpslewis opened this pull request over 1 year ago
Drop to_device, use Flux.gpu / Flux.cpu

jeremiahpslewis opened this pull request over 1 year ago
Github Actions Fixes

jeremiahpslewis opened this pull request over 1 year ago
CI Improvements

jeremiahpslewis opened this pull request over 1 year ago
Hook RewardsPerEpisode broken

CasBex opened this issue over 1 year ago
Drop deprecated @provide interface

jeremiahpslewis opened this pull request over 1 year ago
Add RLZoo and RLExperiments to Buildkite

jeremiahpslewis opened this pull request over 1 year ago
Add Buildkite / GPU tests

jeremiahpslewis opened this pull request over 1 year ago
GPU: Drop to_device Logic and use Flux cpu / gpu functions

jeremiahpslewis opened this pull request over 1 year ago
Use package extensions and KernelAbstractions to make CUDA a weak dependency

jeremiahpslewis opened this pull request over 1 year ago
Use package extensions to make CUDA a weak dependency

jeremiahpslewis opened this pull request over 1 year ago
Reduce find_all_max allocations and increase speed based on chatgpt s…

jeremiahpslewis opened this pull request over 1 year ago
CompatHelper: bump compat for ReinforcementLearningTrajectories to 0.3 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for ReinforcementLearningTrajectories to 0.2 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
Bump flux compat

jeremiahpslewis opened this pull request over 1 year ago
fixing prob. /w symbol/ string correspondence

Mytolo opened this pull request over 1 year ago
fixed DQNLearner Gpu isse

Mytolo opened this pull request over 1 year ago
fixed devmode / project files

Mytolo opened this pull request over 1 year ago
CompatHelper: bump compat for Flux to 0.14 for package ReinforcementLearningExperiments, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for Flux to 0.14 for package ReinforcementLearningZoo, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for Flux to 0.14 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for ReinforcementLearningTrajectories to 0.2 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
EpisodeSampler in Trajectories

HenriDeh opened this issue over 1 year ago
refactored multi agent proposal

Mytolo opened this pull request over 1 year ago
adjusted pettingzoo to PettingZooEnv simultaneous environment more co…

Mytolo opened this pull request over 1 year ago
CompatHelper: bump compat for ReinforcementLearningTrajectories to 0.2 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
CompatHelper: bump compat for ReinforcementLearningTrajectories to 0.2 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
added first Independent Q Learning experiment

Mytolo opened this pull request over 1 year ago
Rework the run loop

HenriDeh opened this pull request over 1 year ago
MultithreadedEnvs and Trajectories

HenriDeh opened this issue over 1 year ago
couple of improvements to MPO

HenriDeh opened this pull request over 1 year ago
Devmode is not working

Mytolo opened this issue over 1 year ago
PPO with MaskedPPOTrajectory

navaxel opened this issue over 1 year ago
ppo update function corrected

navaxel opened this pull request over 1 year ago
Fix Timer bug

jeremiahpslewis opened this pull request over 1 year ago
Add performance testing run loop

jeremiahpslewis opened this pull request over 1 year ago
Executing RLBase.plan! after end of experiment

Mytolo opened this issue over 1 year ago
Loading a Gym Environment

EliottEccidio opened this issue over 1 year ago
Bump RLZoo version for NNlib

jeremiahpslewis opened this pull request over 1 year ago
PPo policy experiments failing

EliottEccidio opened this issue over 1 year ago
QBasedPolicy optimise! forwards to learner.

HenriDeh opened this pull request over 1 year ago
Vectorized environments

sash-a opened this issue over 1 year ago
Fix dispatch and update documentation

HenriDeh opened this pull request over 1 year ago
CompatHelper: bump compat for NNlib to 0.9 for package ReinforcementLearningZoo, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
Swap out rng code

jeremiahpslewis opened this pull request over 1 year ago
Use correct default rng code

jeremiahpslewis opened this pull request over 1 year ago
Breaking changes to optimise! interface: Bump RLCore to v0.11 and RLZoo to v0.8

jeremiahpslewis opened this pull request over 1 year ago
Bug fix optimise!

jeremiahpslewis opened this pull request over 1 year ago
is_terminated return type is unexpected in multi_threaded_env

Graeme22 opened this issue over 1 year ago
fix bug in masked, multi-dimensional state space multi-threaded envs

Graeme22 opened this pull request over 1 year ago
Sketch out optimise! refactor

jeremiahpslewis opened this pull request over 1 year ago
fixed problem with sequential multi agent envs

Mytolo opened this pull request over 1 year ago
NFQ

CasBex opened this pull request over 1 year ago
Update implement new alg docs

jeremiahpslewis opened this pull request over 1 year ago
Contribute Neural Fitted Q-iteration algorithm

CasBex opened this issue over 1 year ago
CompatHelper: add new compat entry for DelimitedFiles at version 1 for package ReinforcementLearningEnvironments, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
reintroduce args kwargs

HenriDeh opened this pull request over 1 year ago
Add deprecation warnings to non-refactored policies

jeremiahpslewis opened this issue over 1 year ago
Fix stack

HenriDeh opened this pull request over 1 year ago
allow more recent versions

HenriDeh opened this pull request over 1 year ago
Stacknamespace

HenriDeh opened this pull request over 1 year ago
CompatHelper: bump compat for ReinforcementLearningZoo to 0.6 for package ReinforcementLearningExperiments, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago
Fix hook issues

jeremiahpslewis opened this pull request over 1 year ago
LoadError: UndefVarError: `params` not defined

UnnamedMoose opened this issue over 1 year ago
Fix Experiment type setup

jeremiahpslewis opened this issue over 1 year ago
Use multiple dispatch / methods plan! and act!

jeremiahpslewis opened this pull request over 1 year ago