taku-y/border

Issues

• [v0.0.8] Add behavior cloning agent

  #26 opened 2 months ago by taku-y
  2

• [v0.0.8] Bump the version of candle to 0.6.0

  #29 opened a month ago by taku-y
  0

• [v0.0.8] Bump the version of candle

  #27 opened a month ago by taku-y
  1

• [v0.0.8] implement `DummyEnv` in a crate

  #28 opened a month ago by taku-y
  0

• [v0.0.8] Support minari

  #17 opened 5 months ago by taku-y
  3

• [v0.0.8] Consider removing the type parameter from Configurable<E: Env>

  #22 opened 2 months ago by taku-y
  1

• [v0.0.8] Consider to remove build() method from Env trait.

  #25 opened 2 months ago by taku-y
  1

• [v0.0.8] Move definitions of conversion functions between ndarray and tensor

  #24 opened 2 months ago by taku-y
  1

• [v0.0.7] Add n_actors as params of mlflow in dqn_atari_async example

  #16 opened 2 months ago by taku-y
  1

• [v0.0.7] Verifying the behavior of mlflow-export-import

  #23 opened 2 months ago by taku-y
  2

• [v0.0.7] Add MLP policy not depending on any deep learning backend

  #19 opened 2 months ago by taku-y
  1

• [v0.0.7] Improve interface of config of agent

  #21 opened 4 months ago by taku-y
  0

• [v0.0.7] Bump the version of clap in examples

  #20 opened 4 months ago by taku-y
  0

• [v0.0.7] Improve code structure for batch and replay buffer

  #18 opened 4 months ago by taku-y
  0

• [v0.0.7] Support specifying the number of threads for tch in Dqn

  #14 opened 6 months ago by taku-y
  0

• [v0.0.7] Fix the error when async trainer finishes

  #15 opened 6 months ago by taku-y
  0

• Support mixed precision in Dqn

  #13 opened 6 months ago by taku-y
  0

• [v0.0.7] Make Policy and Agent to be object safe

  #12 opened 6 months ago by taku-y
  0

• [v0.0.7] Add terminate and truncate in step function API

  #10 opened 6 months ago by taku-y
  0

• [v0.0.7] Add candle agents

  #1 opened 6 months ago by taku-y
  0

• [v0.0.7] Log model parameters in DQN during training

  #9 opened 6 months ago by taku-y
  0

• [v0.0.7] Use MLflow in some examples

  #3 opened 6 months ago by taku-y
  0

• [v0.0.7] Improve README for example programs

  #11 opened 6 months ago by taku-y
  0

• [v0.0.7] Store then log pattern for recorder

  #7 opened 6 months ago by taku-y
  0

• [v0.0.7] Move warmup logic from agent to trainer

  #8 opened 6 months ago by taku-y
  0

• [v0.0.7] Bump the version of tch

  #6 opened 7 months ago by taku-y
  0

• [v0.0.7] Bump the version of candle to 0.4.1

  #5 opened 7 months ago by taku-y
  0

• [v0.0.7] Modify an argument of `Trainer::train()`

  #4 opened 7 months ago by taku-y
  0

• [v0.0.7] Support MLflow tracking

  #2 opened 7 months ago by taku-y
  1