Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / aravindr93/mjrl issues and pull requests

#52 - المغرب

Issue - State: open - Opened by Abderrazak20 7 months ago

#51 - Pvr beta 1vk

Pull Request - State: open - Opened by ElyasYassin 9 months ago

#50 - What's the intuition behind act_repeat ?

Issue - State: open - Opened by rebecajohn about 1 year ago

#49 - gail

Issue - State: open - Opened by lzl60109 over 1 year ago

#48 - Users can now specify and pass wandb details from the config files

Pull Request - State: open - Opened by vikashplus over 1 year ago

#47 - Hyperparams for D4RL Mujoco tasks

Issue - State: open - Opened by joseluperez1999 over 2 years ago

#46 - Understanding obs_mask

Issue - State: open - Opened by mohakbhardwaj almost 3 years ago - 1 comment

#44 - NPG kl_mean is always 0

Issue - State: open - Opened by akjayant about 3 years ago

#43 - add outputdic for player specific color spaces

Pull Request - State: open - Opened by Vittorio-Caggiano over 3 years ago

#42 - Not learning reward?

Issue - State: open - Opened by IanWangg over 3 years ago - 3 comments

#41 - Fixing ndarray warning

Pull Request - State: closed - Opened by girifb over 3 years ago - 1 comment

#40 - RuntimeError: CUDA out of memory.

Issue - State: closed - Opened by pcheng2 over 3 years ago

#39 - Isolating multiprocessing change

Pull Request - State: open - Opened by girifb over 3 years ago - 2 comments

#37 - Changing maxtasksperchild to default

Pull Request - State: closed - Opened by girifb over 3 years ago

#36 - Actions not clipped when generating synthetic trajectories

Issue - State: open - Opened by symoon11 almost 4 years ago

#35 - Experimental results of MoREL for D4RL benchmarks

Issue - State: open - Opened by stevenyangyj almost 4 years ago - 8 comments

#34 - kwargs passthrough for behavior cloning and dapg

Pull Request - State: closed - Opened by aravindr93 about 4 years ago

#33 - Pushing version v1 to master

Pull Request - State: closed - Opened by aravindr93 about 4 years ago - 1 comment

#32 - Pass Loggers + Avoid Multiple Calls.

Pull Request - State: open - Opened by vikashplus over 4 years ago

#31 - Unnecessary imports. Can be cleaned

Issue - State: open - Opened by vikashplus over 4 years ago

#30 - Make training job resumable if pointed to the same training folder

Pull Request - State: closed - Opened by vikashplus over 4 years ago

#29 - Ignore sporadic warnings that make the env crash and jobs terminate

Pull Request - State: open - Opened by vikashplus over 4 years ago - 1 comment

#28 - FEATURE: pre-loaded sim can be passed to create envs

Pull Request - State: closed - Opened by vikashplus over 4 years ago

#27 - Pickling of _VariableFunctions not compatible with PyTorch 1.5.0

Issue - State: closed - Opened by chinmay-singh over 4 years ago - 1 comment

#26 - why are the advantages multiplied by 1e-2 in dapg.py?

Issue - State: closed - Opened by henrycharlesworth over 4 years ago - 1 comment

#25 - Sampler timeouts when running many concurrent trainings

Issue - State: closed - Opened by Jendker almost 5 years ago

#24 - No RBF code?

Issue - State: open - Opened by Haoxiang-Wang almost 5 years ago

#23 - Adding dtype to the boxes to avoid warning messages from gym

Pull Request - State: closed - Opened by vikashplus about 5 years ago

#22 - Merge redesign with master

Pull Request - State: closed - Opened by aravindr93 about 5 years ago

#21 - Gpu policy patch

Pull Request - State: closed - Opened by bennevans about 5 years ago - 1 comment

#20 - Gpu policy patch

Pull Request - State: closed - Opened by bennevans about 5 years ago

#19 - Unable to complete the installation from the provided yml file

Issue - State: closed - Opened by priyankamandikal over 5 years ago - 1 comment

#18 - Make training job resumable

Pull Request - State: open - Opened by wookayin over 5 years ago

#17 - Much worse learning performance with new code base

Issue - State: closed - Opened by Jendker over 5 years ago - 4 comments

#16 - Fix a bug in trajectory_sampler

Pull Request - State: closed - Opened by wookayin over 5 years ago - 1 comment

#15 - Hand vil core

Pull Request - State: open - Opened by Divye02 over 5 years ago

#14 - added evalua_policy_vil in gym_env

Pull Request - State: open - Opened by Divye02 over 5 years ago

#13 - [Question] Meaning of the "al" variable?

Issue - State: closed - Opened by araffin almost 6 years ago - 4 comments

#12 - evaluate success can accept logger to log multiple statistics

Pull Request - State: closed - Opened by aravindr93 about 6 years ago

#12 - evaluate success can accept logger to log multiple statistics

Pull Request - State: closed - Opened by aravindr93 about 6 years ago

#11 - Value function approximator

Issue - State: closed - Opened by supratikp about 6 years ago - 1 comment

#10 - Is mean KL always zero?

Issue - State: closed - Opened by tpbarron over 6 years ago - 1 comment

#9 - Fix attribute error with new version of gym.

Pull Request - State: closed - Opened by zafarali over 6 years ago - 1 comment

#8 - Small typos in the readme

Issue - State: closed - Opened by vikashplus over 6 years ago

#7 - difference between `a is b` and `a == b`

Issue - State: closed - Opened by aravindr93 over 6 years ago

#6 - missing packages in conda env build

Issue - State: closed - Opened by aravindr93 over 6 years ago - 1 comment

#5 - adding dapg into master

Pull Request - State: closed - Opened by aravindr93 over 6 years ago

#4 - adding behavior cloning ver1

Pull Request - State: closed - Opened by aravindr93 over 6 years ago

#3 - linear policy?

Issue - State: closed - Opened by zafarali over 6 years ago - 5 comments

#2 - moving linear policies to different repo

Pull Request - State: closed - Opened by aravindr93 almost 7 years ago

#1 - initial commit

Pull Request - State: closed - Opened by aravindr93 almost 7 years ago