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
How to pretrain a model with behavior cloning RLlib	14	5710	December 5, 2023
Reproducible training - setting seeds for all workers / environments RLlib	18	6598	May 6, 2023
RLLIB not working with Tune with sample batch input RLlib	25	2895	October 4, 2022
ValueError: Expected parameter logits (...) to satisfy the constraint IndependentConstraint(Real(), 1) RLlib	38	9706	October 14, 2024
_winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] RLlib	9	18907	May 14, 2022
RLlib Office Hours - Now open for signup RLlib	13	1490	July 1, 2025
[RLlib] Impossible actions RLlib	12	4304	May 11, 2022
Ray for Rapberry Pi, is possible? RLlib	30	4752	February 23, 2021
Multi-Agent Training with Different Algorithms RLlib	24	4200	October 11, 2022
Observation_space not provided in PolicySpec RLlib	21	7709	February 7, 2023
[RLlib] Visualise custom environment RLlib	18	4430	March 30, 2021
Issues reproducing stable-baselines3 PPO performance with rllib RLlib	14	3024	March 16, 2022
Resume=True fails without useful error message RLlib	31	3656	September 26, 2022
Help debugging a memory leak in rllib RLlib	21	4288	September 25, 2022
Board game self-play PPO RLlib	15	4479	May 4, 2021
RNN L2 weights regularization RLlib	41	2639	July 5, 2021
Issue creating custom action mask enviorment RLlib	14	2408	October 11, 2023
Use Policy_Trainer with TensorBoard RLlib	33	2835	November 13, 2021
Deploying a learned policy under "explore=False / True" RLlib	9	1640	March 17, 2022
Removing Algorithms from RLlib RLlib	10	1546	July 22, 2022
RLlib, PyTorch and Mac M1 GPUs: No available node types can fulfill resource request RLlib	11	4590	February 29, 2024
Compute_actions for Trajectory API RLlib	11	2579	February 10, 2022
Issue with custom LSTMs RLlib	34	2544	February 26, 2023
Meaning of episode_reward_mean RLlib	10	4525	September 21, 2023
Is any multi discrete action example for PPO or other algorithms? RLlib	9	4701	January 29, 2023
Observation space with multiple input RLlib	15	3705	December 10, 2021
Unable to restore fully trained checkpoint RLlib	19	3218	October 21, 2023
Missing 'grad_gnorm' key in some `input_trees` after some training time RLlib	23	2577	January 29, 2023
How to define fcnet_hiddens size and number of layers in rllib tune? RLlib	18	2782	January 19, 2023
Apply preprocessor in custom model RLlib	19	2700	May 13, 2024
How do I set GPU affinity of workers RLlib	17	2754	April 23, 2021
RLLib Multiagent: Load only one policy from checkpoint & Compatibility of RLLib/Tune Checkpoints RLlib	9	3498	November 24, 2021
Compute/display actions from ray.tune RLlib	10	1829	March 30, 2021
Stacking callback objects [Solved. Code included.] RLlib	12	1669	April 30, 2021
Very slow gradient descent on remote workers RLlib	14	2664	June 8, 2021
Best way to have custom value state + LSTM RLlib	9	3259	April 10, 2022
Right way to use tuple action space RLlib	9	1773	September 24, 2021
Maximum recommended reward RLlib	18	2273	July 14, 2022
Accessing info dicts in postprocessing callback RLlib	10	1544	January 11, 2021
Custom RNN Model with Examples - why do they fail? RLlib	11	2505	May 5, 2022
Global optima with centralized critic (basic understanding) RLlib	10	2553	April 10, 2021
How to log Render to tensorboard? RLlib	9	2646	July 22, 2021
Reward function not converging during training RLlib	14	2103	July 11, 2022
PPO trainer eating up memory RLlib	9	2543	April 2, 2021
Get agent ID in multi-agent setting RLlib	16	1941	October 5, 2021
[Bug] Env must be one of the supported types: BaseEnv, gym.Env, MultiAgentEnv, VectorEnv, RemoteBaseEnv RLlib	10	2383	March 2, 2023
Memory Leak when training PPO on a single agent environment RLlib	15	1962	December 24, 2022
RLlib's PolicyServer and external simulator as client RLlib	15	1942	April 12, 2021
Playing the QMIX Two-step game on Ray RLlib	11	2216	October 18, 2022
Error with torch policy and ray.get_gpu_ids on Windows RLlib	9	1362	July 30, 2021