issues
search
vwxyzjn
/
cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
http://docs.cleanrl.dev
Other
5.54k
stars
631
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Documentation improvement - fix links and mkdocs
#181
vwxyzjn
closed
2 years ago
2
Update issue_template.md
#180
vwxyzjn
closed
2 years ago
2
SAC doesn't work
#179
vadim0x60
closed
2 years ago
7
Proper multi-gpu support with PPO
#178
vwxyzjn
closed
2 years ago
3
Update README.md
#177
ElliotMunro200
closed
2 years ago
3
Wrong direction in readme.md file
#176
ElliotMunro200
closed
2 years ago
2
Please specify in readme.md that is for Python3.8-3.9. 3.8+ is misleading because 3.10 leads to problems
#175
ElliotMunro200
closed
2 years ago
5
Add docs header
#174
vwxyzjn
closed
2 years ago
2
Refactor replay based scripts
#173
vwxyzjn
closed
2 years ago
5
TD3 should also log losses for `qf2`
#172
vwxyzjn
closed
2 years ago
0
Seed issue with `dqn.py` and others
#171
vwxyzjn
closed
2 years ago
0
Removes unmaintained scripts
#170
vwxyzjn
closed
2 years ago
2
Address stale documentation
#169
vwxyzjn
closed
2 years ago
2
Also log `episodic_length` for non-PPO scripts.
#168
vwxyzjn
closed
2 years ago
0
Various minor PPO refactors
#167
vwxyzjn
closed
10 months ago
1
Enable video recording for `ppo_procgen.py`
#166
vwxyzjn
closed
2 years ago
2
Introduce benchmark utilities
#165
vwxyzjn
closed
2 years ago
4
Change `ppo.py`'s default timesteps
#164
vwxyzjn
closed
2 years ago
2
Add PPO documentation
#163
vwxyzjn
closed
2 years ago
3
Prototype multi-gpu support with PPO
#162
vwxyzjn
closed
2 years ago
8
Let `ppo_continuous_action.py`only run 1M steps
#161
vwxyzjn
closed
2 years ago
2
Fix the default wandb project name in `ppo_atari_envpool.py`
#160
vwxyzjn
closed
2 years ago
2
Add docs for `c51.py` and `c51_atari.py`
#159
vwxyzjn
closed
2 years ago
4
Auto-upgrade syntax via `pyupgrade`
#158
vwxyzjn
closed
2 years ago
3
Add docs for `dqn.py`
#157
vwxyzjn
closed
2 years ago
6
Investigate DQN's regression in `MountainCar-v0`
#156
vwxyzjn
closed
2 years ago
1
KeyError: "terminal_observation" in dqn.py
#155
Jackory
closed
2 years ago
3
Introduce better contribution guide
#154
vwxyzjn
closed
2 years ago
2
Added License info regarding SAC
#153
dosssman
closed
2 years ago
2
Amend license to give proper attribution
#152
vwxyzjn
closed
2 years ago
6
Add rnd_ppo.py documentation and refactor
#151
yooceii
closed
2 years ago
5
Preview Logo 1
#150
vwxyzjn
closed
2 years ago
2
Bump paramiko from 2.9.2 to 2.10.1
#149
dependabot[bot]
closed
2 years ago
3
Investigate ` nn.utils.clip_grad_norm_` for DQN, DDPG, and TD3
#148
vwxyzjn
closed
2 years ago
3
Bump opencv-python from 3.4.17.61 to 4.2.0.32 in /requirements
#147
dependabot[bot]
closed
2 years ago
3
SAC Documentation - Benchmarks - Minor code tweaks
#146
dosssman
closed
2 years ago
9
DDPG documnetation tweaks; added Q loss equations and light explanation
#145
dosssman
closed
2 years ago
6
Support pettingzoo MA ALE envs with PPO
#144
vwxyzjn
closed
2 years ago
3
Export `requirements.txt` automatically
#143
vwxyzjn
closed
2 years ago
2
Fix incorrect links in the DDPG docs
#142
vwxyzjn
closed
2 years ago
2
Add documentation for `td3_continuous_action.py`
#141
vwxyzjn
closed
2 years ago
4
Fix typo in DDPG docs
#140
vwxyzjn
closed
2 years ago
2
Fix DDPG docs' description
#139
vwxyzjn
closed
2 years ago
3
Update to `gym==0.23.1`
#138
vwxyzjn
closed
2 years ago
2
Add `ddpg_continuous_action.py` docs
#137
vwxyzjn
closed
2 years ago
5
Deprecate `apex_dqn_atari.py`
#136
vwxyzjn
closed
2 years ago
2
Remove offline DQN scripts
#135
vwxyzjn
closed
2 years ago
4
Make seed work again in value methods
#134
vwxyzjn
closed
2 years ago
3
`dqn.py` does not respect seed
#133
vwxyzjn
closed
2 years ago
1
Deprecating `apex_dqn_atari.py`
#132
vwxyzjn
closed
2 years ago
0
Previous
Next