DeepX-inc/machina

Issues

• Quickstart issue

  #266 opened 3 years ago by nikkujensen
  0

• How to implement Meta-RL algorithm like MAML

  #265 opened 4 years ago by Katsumi-N
  0

• Validation of QT-Opt

  #264 opened 4 years ago by leinxx
  1

• Executed run ppo.py,RuntimeError: CUDA error: device-side assert triggered occured.

  #261 opened 4 years ago by hosokawa-taiji
  5

• Executed run_r2d2_sac.py,`BrokenPipeError: [Errno 32] Broken pipe` occurred.

  #260 opened 5 years ago by hosokawa-taiji
  9

• Executed run_ppo.py,RuntimeError: size mismatch occurred.

  #258 opened 5 years ago by hosokawa-taiji
  8

• Example script of DDPG seems incorrect

  #254 opened 5 years ago by caprest
  2

• max_ent in example/run_sac.py is not used

  #255 opened 5 years ago by caprest
  1

• Some refactoring to files in pols directory

  #252 opened 5 years ago by tadashiK
  4

• Can't use CNN?

  #248 opened 5 years ago by yumion
  3

• Add info about which type of action space each algorithm supports in READMe

  #245 opened 5 years ago by takerfume
  0

• Implement DQN

  #244 opened 5 years ago by takerfume
  0

• CEMDeterminsticsSAVFunc doesn't support gym.spaces.Discrete

  #242 opened 5 years ago by yumion
  1

• Write DIAYN into `Implemented Algorithms` in Readme

  #237 opened 5 years ago by takerfume
  0

• Rename ob_space and ac_space to observation_space and action_space

  #230 opened 5 years ago by takerfume
  1

• CEMDeterminsticsSAVFunc take too much batch_size.

  #221 opened 5 years ago by iory
  2

• Enpty rows in progress.vsv

  #225 opened 5 years ago by swdr1904
  4

• Make document pages

  #213 opened 5 years ago by takerfume
  3

• Complete lacked docstrings

  #228 opened 5 years ago by takerfume
  1

• Support gym.spaces.Dict

  #216 opened 5 years ago by iory
  2

• Fix options for ppo and trpo with rnn

  #192 opened 5 years ago by takerfume
  4

• Use default device manager in PyTorch

  #214 opened 5 years ago by rarilurelo
  0

• Add option of bptt's length

  #209 opened 5 years ago by rarilurelo
  0

• Dataparallel Option in PPO Cause Error

  #202 opened 5 years ago by takerfume
  2

• Inappropriate mean in loss_functional with rnn

  #118 opened 5 years ago by rarilurelo
  1

• Add names of implemented algorithms to readme

  #152 opened 5 years ago by rarilurelo
  0

• Managing number of steps in a batch

  #119 opened 6 years ago by rarilurelo
  1

• Implementation of R2D2

  #111 opened 5 years ago by rarilurelo
  1

• Allocate Traj's tensor to cpu

  #121 opened 5 years ago by rarilurelo
  1

• TD3

  #193 opened 5 years ago by takerfume
  1

• Faster sampling in random batch

  #179 opened 5 years ago by rarilurelo
  1

• Add N-distill

  #176 opened 5 years ago by pwuethri
  1

• Example code does not run anymore

  #180 opened 5 years ago by pwuethri
  1

• Data parallel on CEMDeteminisiticSAVfunc

  #172 opened 5 years ago by rarilurelo
  1

• `lf.likelihood` seems to be log-likelihood

  #168 opened 5 years ago by rarilurelo
  2

• Test for new algorithm

  #139 opened 5 years ago by rarilurelo
  2

• More general hs (hidden state)

  #167 opened 5 years ago by rarilurelo
  0

• Remove pds (probabilistic distributions) class and incorporating to pol (policy) class.

  #166 opened 5 years ago by rarilurelo
  0

• log_std referenced before assignment

  #161 opened 5 years ago by jtoyama4
  2

• Write meanings of args

  #133 opened 6 years ago by takerfume
  1

• Testing policy distillation

  #155 opened 6 years ago by pwuethri
  2

• Add Explanation about Imitation Learning

  #142 opened 6 years ago by takerfume
  0

• Script for taking movies of learned policy

  #132 opened 6 years ago by takerfume
  0

• Use cpu_mode in sampling phase

  #143 opened 6 years ago by rarilurelo
  1

• QT-Opt

  #130 opened 6 years ago by takerfume
  1

• Adversarial Inverse Reinforcement Learning

  #122 opened 6 years ago by takerfume
  1

• Variational Discriminator Bottleneck

  #129 opened 6 years ago by takerfume
  0

• Learning Self-Imitating Diverse Policies

  #125 opened 6 years ago by takerfume
  0

• Wrapper environment in which observation includes reward

  #114 opened 6 years ago by rarilurelo
  1

• Wrapper environment in which observation includes action

  #113 opened 6 years ago by rarilurelo
  1