JuliaReinforcementLearning/ReinforcementLearning.jl

Issues

• ReinforcementLearning.jl v0.12

  #1061 opened 10 months ago by jeremiahpslewis
  20

• Wrong style for state report for TicTacToeEnv()

  #1079 opened 5 months ago by hespanha
  2

• Needless allocations in reward() and is_terminated() for

  #1080 opened 5 months ago by hespanha
  0

• Does it allow defining an environment that has continuous action space? And how?

  #1078 opened 6 months ago by WuSiren
  4

• It's not feasible to update the Q-based value agent in large steps for the RandomWalk1D() environment.

  #1068 opened 9 months ago by Van314159
  10

• No method matching iterate ArrayProductDomain

  #1074 opened 8 months ago by ZdM87
  5

• Algorithm implementations

  #1070 opened 9 months ago by johannes-fischer
  1

• Overspecific types in built-in policies and algorithms

  #1066 opened 9 months ago by dharux
  2

• ElasticArraySARTSTraces does not record the trajectories of `MountainCarEnv()` correctly

  #1067 opened 9 months ago by Van314159
  7

• Update Website, fix broken references / issues

  #1060 opened 10 months ago by jeremiahpslewis
  4

• MultithreadedEnvs and Trajectories

  #920 opened 2 years ago by HenriDeh
  1

• Improving Collaboration: Separate out the environment interface

  #954 opened a year ago by zsunberg
  4

• Missing features in RLCore

  #961 opened a year ago by HenriDeh
  0

• is_terminated return type is unexpected in multi_threaded_env

  #901 opened 2 years ago by Graeme22
  1

• Loading a Gym Environment

  #912 opened 10 months ago by EliottEccidio
  4

• TD3 Policy unable to handle environments with multidimensional action spaces

  #951 opened 10 months ago by gggoes
  3

• experiments failed

  #982 opened 10 months ago by Yue-Wang-qvp
  2

• TicTacToeEnv allows illegal moves

  #1001 opened a year ago by colintbowers
  0

• Add deprecation warnings to non-refactored policies

  #892 opened 10 months ago by jeremiahpslewis
  3

• Vectorized environments

  #908 opened 10 months ago by sash-a
  3

• Spin off core packages

  #960 opened 10 months ago by jeremiahpslewis
  3

• Breaking the tutorial by getting TotalRewardPerEpisode out of sync with the stopping condition in a `run` call

  #1000 opened 10 months ago by colintbowers
  0

• PPO with MaskedPPOTrajectory

  #917 opened 10 months ago by navaxel
  3

• Devmode is not working

  #918 opened 10 months ago by Mytolo
  3

• Transfer Algorithms to RLFarm

  #1028 opened 10 months ago by jeremiahpslewis
  17

• Website: A practical introduction to RL: Does not introduce, source code is broken

  #1036 opened 10 months ago by joelreymont
  1

• Update ReinforcementLearningAnIntroduction to be v0.11 compatible

  #1063 opened 10 months ago by jeremiahpslewis
  0

• Update Buildkite script for gpu testing so it's sub package compatible

  #1030 opened 10 months ago by jeremiahpslewis
  0

• Review TabularApproximator

  #1039 opened 10 months ago by jeremiahpslewis
  6

• Website: How do implement a new algorithm is outdated

  #1037 opened 10 months ago by joelreymont
  1

• Simple ReinforcementLearning example crashes

  #1034 opened 10 months ago by ropewe56
  5

• RL Core tests fail sporadically

  #1010 opened 10 months ago by joelreymont
  15

• CI: Should spell check be dropped or fixed?

  #1026 opened 10 months ago by joelreymont
  2

• Tutorial OpenSpiel KuhnOpenNSFP fails

  #1024 opened 10 months ago by finmod
  6

• GPU Compile error on PPO with MaskedPPOTrajectory

  #1007 opened a year ago by qwjyh
  0

• RL Env tests fail with latest OpenSpiel patches

  #1011 opened a year ago by joelreymont
  1

• params() is no longer supported in Flux

  #996 opened a year ago by halyusuf25
  1

• Fixing SAC Policy

  #970 opened a year ago by gggoes
  4

• An error

  #983 opened a year ago by zsz00
  0

• LoadError: UndefVarError: `params` not defined

  #882 opened 2 years ago by UnnamedMoose
  6

• Prioritised DQN failing on GPU

  #973 opened a year ago by CasBex
  0

• Prioritized DQN experiment nonfunctional

  #971 opened a year ago by CasBex
  5

• Can implement this ARZ algorithm ?

  #965 opened a year ago by zsz00
  1

• AssertionError: action in env.action_space

  #967 opened a year ago by ZdM87
  0

• EpisodeSampler in Trajectories

  #927 opened a year ago by HenriDeh
  0

• Hook RewardsPerEpisode broken

  #945 opened a year ago by CasBex
  6

• Executing RLBase.plan! after end of experiment

  #913 opened a year ago by Mytolo
  11

• Contribute Neural Fitted Q-iteration algorithm

  #895 opened 2 years ago by CasBex
  4

• PPo policy experiments failing

  #910 opened 2 years ago by EliottEccidio
  1

• Rename update! to push!

  #883 opened 2 years ago by jeremiahpslewis
  2