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	1691	June 29, 2021
How to pretrain a model with behavior cloning RLlib	14	5324	December 5, 2023
RLLIB not working with Tune with sample batch input RLlib	25	2615	October 4, 2022
_winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] RLlib	9	18303	May 14, 2022
ValueError: Expected parameter logits (...) to satisfy the constraint IndependentConstraint(Real(), 1) RLlib	38	9025	October 14, 2024
RLlib Office Hours - Now open for signup RLlib	14	1340	July 1, 2025
[RLlib] Impossible actions RLlib	12	4079	May 11, 2022
Ray for Rapberry Pi, is possible? RLlib	30	4322	February 23, 2021
Observation_space not provided in PolicySpec RLlib	21	7415	February 7, 2023
[RLlib] Visualise custom environment RLlib	18	4149	March 30, 2021
Multi-Agent Training with Different Algorithms RLlib	24	3572	October 11, 2022
Reproducible training - setting seeds for all workers / environments RLlib	20	6140	May 24, 2023
Help debugging a memory leak in rllib RLlib	21	3922	September 25, 2022
Resume=True fails without useful error message RLlib	31	3224	September 26, 2022
Issues reproducing stable-baselines3 PPO performance with rllib RLlib	14	2537	March 16, 2022
Board game self-play PPO RLlib	15	4078	May 4, 2021
Issue creating custom action mask enviorment RLlib	14	2230	October 11, 2023
Compute_actions for Trajectory API RLlib	11	2431	February 10, 2022
Deploying a learned policy under "explore=False / True" RLlib	9	1452	March 17, 2022
RLlib, PyTorch and Mac M1 GPUs: No available node types can fulfill resource request RLlib	11	4153	February 29, 2024
Meaning of episode_reward_mean RLlib	10	4265	September 21, 2023
Is any multi discrete action example for PPO or other algorithms? RLlib	9	4400	January 29, 2023
Use Policy_Trainer with TensorBoard RLlib	33	2373	November 13, 2021
Observation space with multiple input RLlib	15	3398	December 10, 2021
RNN L2 weights regularization RLlib	41	2060	July 5, 2021
Unable to restore fully trained checkpoint RLlib	19	2961	October 21, 2023
Issue with custom LSTMs RLlib	34	2168	February 26, 2023
Missing 'grad_gnorm' key in some `input_trees` after some training time RLlib	23	2257	January 29, 2023
How to define fcnet_hiddens size and number of layers in rllib tune? RLlib	18	2510	January 19, 2023
How do I set GPU affinity of workers RLlib	17	2502	April 23, 2021
Apply preprocessor in custom model RLlib	19	2360	May 13, 2024
RLLib Multiagent: Load only one policy from checkpoint & Compatibility of RLLib/Tune Checkpoints RLlib	9	3310	November 24, 2021
Compute/display actions from ray.tune RLlib	10	1684	March 30, 2021
Best way to have custom value state + LSTM RLlib	9	3084	April 10, 2022
Very slow gradient descent on remote workers RLlib	14	2465	June 8, 2021
Stacking callback objects [Solved. Code included.] RLlib	12	1464	April 30, 2021
Right way to use tuple action space RLlib	9	1600	September 24, 2021
Maximum recommended reward RLlib	18	1956	July 14, 2022
Accessing info dicts in postprocessing callback RLlib	10	1421	January 11, 2021
Custom RNN Model with Examples - why do they fail? RLlib	11	2362	May 5, 2022
How to log Render to tensorboard? RLlib	9	2483	July 22, 2021
Global optima with centralized critic (basic understanding) RLlib	10	2353	April 10, 2021
PPO trainer eating up memory RLlib	9	2364	April 2, 2021
[Bug] Env must be one of the supported types: BaseEnv, gym.Env, MultiAgentEnv, VectorEnv, RemoteBaseEnv RLlib	10	2222	March 2, 2023
Reward function not converging during training RLlib	14	1868	July 11, 2022
Error when running on GPU RLlib	9	2282	February 23, 2022
Error with torch policy and ray.get_gpu_ids on Windows RLlib	9	1247	July 30, 2021
RLlib's PolicyServer and external simulator as client RLlib	15	1752	April 12, 2021
Get agent ID in multi-agent setting RLlib	16	1697	October 5, 2021
Playing the QMIX Two-step game on Ray RLlib	11	2014	October 18, 2022