RLlib

Debugging and performance tuning Steps to contribute to RLlib Configure Algorithm, Training, Evaluation, Scaling Repeated observation space Ray Tune stopping condition & comparisons Offline RL Checkpointing, Restoring

Topic	Replies	Views	Activity
RLlib beginners tutorial at this year's Ray Summit (June 22nd-24th)! RLlib	11	1728	June 29, 2021
How to pretrain a model with behavior cloning RLlib	14	5429	December 5, 2023
RLLIB not working with Tune with sample batch input RLlib	25	2677	October 4, 2022
_winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] RLlib	9	18491	May 14, 2022
ValueError: Expected parameter logits (...) to satisfy the constraint IndependentConstraint(Real(), 1) RLlib	38	9129	October 14, 2024
RLlib Office Hours - Now open for signup RLlib	14	1363	July 1, 2025
[RLlib] Impossible actions RLlib	12	4115	May 11, 2022
Ray for Rapberry Pi, is possible? RLlib	30	4398	February 23, 2021
Observation_space not provided in PolicySpec RLlib	21	7474	February 7, 2023
Multi-Agent Training with Different Algorithms RLlib	24	3686	October 11, 2022
[RLlib] Visualise custom environment RLlib	18	4198	March 30, 2021
Reproducible training - setting seeds for all workers / environments RLlib	20	6202	May 24, 2023
Help debugging a memory leak in rllib RLlib	21	4025	September 25, 2022
Resume=True fails without useful error message RLlib	31	3336	September 26, 2022
Issues reproducing stable-baselines3 PPO performance with rllib RLlib	14	2663	March 16, 2022
Board game self-play PPO RLlib	15	4156	May 4, 2021
Issue creating custom action mask enviorment RLlib	14	2276	October 11, 2023
Deploying a learned policy under "explore=False / True" RLlib	9	1516	March 17, 2022
Compute_actions for Trajectory API RLlib	11	2455	February 10, 2022
RLlib, PyTorch and Mac M1 GPUs: No available node types can fulfill resource request RLlib	11	4261	February 29, 2024
Meaning of episode_reward_mean RLlib	10	4340	September 21, 2023
Use Policy_Trainer with TensorBoard RLlib	33	2452	November 13, 2021
Is any multi discrete action example for PPO or other algorithms? RLlib	9	4479	January 29, 2023
Removing Algorithms from RLlib RLlib	10	1346	July 22, 2022
RNN L2 weights regularization RLlib	41	2165	July 5, 2021
Observation space with multiple input RLlib	15	3467	December 10, 2021
Unable to restore fully trained checkpoint RLlib	19	3016	October 21, 2023
Issue with custom LSTMs RLlib	34	2229	February 26, 2023
Missing 'grad_gnorm' key in some `input_trees` after some training time RLlib	23	2354	January 29, 2023
How to define fcnet_hiddens size and number of layers in rllib tune? RLlib	18	2556	January 19, 2023
Apply preprocessor in custom model RLlib	19	2471	May 13, 2024
How do I set GPU affinity of workers RLlib	17	2558	April 23, 2021
RLLib Multiagent: Load only one policy from checkpoint & Compatibility of RLLib/Tune Checkpoints RLlib	9	3351	November 24, 2021
Compute/display actions from ray.tune RLlib	10	1707	March 30, 2021
Best way to have custom value state + LSTM RLlib	9	3126	April 10, 2022
Stacking callback objects [Solved. Code included.] RLlib	12	1530	April 30, 2021
Very slow gradient descent on remote workers RLlib	14	2509	June 8, 2021
Right way to use tuple action space RLlib	9	1647	September 24, 2021
Maximum recommended reward RLlib	18	2002	July 14, 2022
Accessing info dicts in postprocessing callback RLlib	10	1440	January 11, 2021
Custom RNN Model with Examples - why do they fail? RLlib	11	2390	May 5, 2022
Global optima with centralized critic (basic understanding) RLlib	10	2388	April 10, 2021
How to log Render to tensorboard? RLlib	9	2502	July 22, 2021
PPO trainer eating up memory RLlib	9	2406	April 2, 2021
Reward function not converging during training RLlib	14	1931	July 11, 2022
[Bug] Env must be one of the supported types: BaseEnv, gym.Env, MultiAgentEnv, VectorEnv, RemoteBaseEnv RLlib	10	2254	March 2, 2023
Error when running on GPU RLlib	9	2301	February 23, 2022
Get agent ID in multi-agent setting RLlib	16	1747	October 5, 2021
RLlib's PolicyServer and external simulator as client RLlib	15	1789	April 12, 2021
Playing the QMIX Two-step game on Ray RLlib	11	2048	October 18, 2022