tspooner/rsrl

Issues

• Undefined symbols for architecture x86_64: "_cblas_sdot", referenced from

  #79 opened 2 years ago by nbro
  1

• Add support for the RL-Glue protocol.

  #63 opened 5 years ago by tspooner
  1

• Roadmap needed

  #78 opened 2 years ago by nbro
  0

• Not able to run the openai code

  #59 opened 5 years ago by infinite-Joy
  1

• [Question] is this project abandoned?

  #75 opened 3 years ago by trsh
  3

• readme.md's versions may cause errors on MacOS

  #77 opened 3 years ago by Pennswood
  0

• `DerefSlice` is difficult to implement

  #70 opened 4 years ago by joshhansen
  3

• Agents requiring mutability for evaluation (action selection)

  #73 opened 4 years ago by wschella
  8

• How to write custom environments for training on a custom problem?

  #58 opened 5 years ago by infinite-Joy
  3

• `Shared<T>` can't be unwrapped or serialized

  #71 opened 4 years ago by joshhansen
  7

• qns: Saving each experiment run

  #69 opened 4 years ago by alanpoon
  2

• Examples disappeared from master

  #67 opened 4 years ago by Moxinilian
  1

• Can't run examples - linker errors to blas

  #54 opened 5 years ago by Ploppz
  3

• Implicit compatible function approximation

  #45 opened 5 years ago by tspooner
  0

• Add config-based experiment infrastructure.

  #64 opened 5 years ago by tspooner
  0

• Extensibility to multi-agent settings

  #62 opened 5 years ago by drewstone
  2

• Replace calls to Option/Result::unwrap() with proper error handling

  #61 opened 5 years ago by tspooner
  0

• Add some simple divergence detection

  #18 opened 5 years ago by tspooner
  0

• Complete logging support

  #20 opened 6 years ago by tspooner
  0

• Revise trace interface

  #41 opened 6 years ago by tspooner
  0

• Examples don't seem to build

  #53 opened 5 years ago by cholcombe973
  3

• Hyper parameter optimisation as a native feature

  #38 opened 6 years ago by tspooner
  7

• Add support for neural networks

  #33 opened 6 years ago by tspooner
  2

• Why Vector type?

  #51 opened 5 years ago by Ploppz
  1

• Gradient-free policy search methods

  #48 opened 5 years ago by tspooner
  0

• Evolutionary strategies

  #46 opened 5 years ago by tspooner
  0

• Parameterised action spaces

  #47 opened 5 years ago by tspooner
  0

• Reduce code duplication with macros

  #42 opened 6 years ago by tspooner
  0

• Add FQI and variants thereof

  #39 opened 6 years ago by tspooner
  0

• Future-based experiment model

  #31 opened 6 years ago by tspooner
  0

• Add the option-critic architecture

  #36 opened 6 years ago by tspooner
  0

• Add the Horde architecture

  #37 opened 6 years ago by tspooner
  0

• Add support for non-discrete action spaces

  #29 opened 6 years ago by tspooner
  1

• Add policy gradient methods and re-visit `policies` module

  #25 opened 6 years ago by tspooner
  1

• Replace existing implementations with traits from num_traits crate wherever possible.

  #26 opened 6 years ago by tspooner
  0

• Split crate into separate modules

  #23 opened 6 years ago by tspooner
  0

• Adaptive function approximation

  #13 opened 6 years ago by tspooner
  1

• Add state preprocessing module

  #24 opened 6 years ago by tspooner
  1