Issues
- 2
Update compatibility with gym environment
#344 opened by delara38 - 0
Updating Notebooks with the new runner api
#338 opened by hnekoeiq - 0
Masking the DRQN
#325 opened by mrsamsami - 3
- 5
pytorch version update ~=1.6 -> >=1.7
#273 opened by sriyash421 - 2
`_max_steps_per_episode` in the main loop has the issue of not making `done=True`
#285 opened by alirahkay - 1
- 0
Change the test name
#313 opened by hnekoeiq - 0
- 2
Bug with testing episodes
#246 opened by hnekoeiq - 1
Add DDPG, TD3 Agents
#254 opened by dapatil211 - 1
CI/CD dependecy installation
#283 opened by sriyash421 - 0
Add RLiable metrics
#255 opened by dapatil211 - 0
- 1
Buffer for on-policy algorithms like PPO, TRPO
#271 opened by sriyash421 - 0
Add PPO Agent
#253 opened by dapatil211 - 0
Jax DQN
#252 opened by dapatil211 - 0
Add Atari 100k
#251 opened by dapatil211 - 0
Recurrent DQN Agent
#250 opened by dapatil211 - 0
Create a Recurrent Replay Buffer
#249 opened by dapatil211 - 0
[README] Have a section in README on how to change config from CL. (Difference between complex objects and basic parameters)
#165 opened by dapatil211 - 0
- 0
- 0
Base.py #124 check if the train_mode is already True.
#164 opened by dapatil211 - 2
- 0
Update Atari Env to v5
#172 opened by dapatil211 - 0
Add agent-specific seed for multiple agents
#167 opened by dapatil211 - 0
Add the global seed
#158 opened by alirahkay - 0
Do testing over a fixed number of testing episodes. (10 episodes per one test)
#163 opened by dapatil211 - 0
- 0
- 0
add a small number to avoid numericall issues
#181 opened by hnekoeiq - 0
Change the initial replay buffer to the efficient replay buffer. Also change name of efficient buffer
#166 opened by dapatil211 - 0
- 0
Can't tuple an int
#173 opened by saikrishna-1996 - 0
- 0
Dqn.py #202 Add a comment on breaking argmax tie.
#171 opened by dapatil211 - 1
Testing epsilon should not be zero.
#96 opened by alirahkay - 1
Create an option for saving a run based on the number of training frames. (In the saving schedule)
#133 opened by alirahkay - 0
Fix logging multi-agent wandb params
#137 opened by hnekoeiq - 0
Change wandb settings to fork
#131 opened by dapatil211 - 0
Add update period to the rainbow
#122 opened by alirahkay - 0
test episodes should not add to training steps
#125 opened by hnekoeiq - 0
log average testing performance
#112 opened by hnekoeiq - 3
Frame Stacking is still not working in `conv.py`
#114 opened by alirahkay - 0
- 0
Debugging metrics
#100 opened by dapatil211 - 0
Probe environments
#99 opened by dapatil211 - 0
Create Debugging tools
#98 opened by dapatil211 - 1
`EfficientCircularBuffer` uses *capacity*, whereas `CircularReplayBuffer` uses *size*.
#97 opened by alirahkay