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	1630	June 29, 2021
How to pretrain a model with behavior cloning RLlib	14	5123	December 5, 2023
RLLIB not working with Tune with sample batch input RLlib	25	2552	October 4, 2022
_winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] RLlib	9	17407	May 14, 2022
ValueError: Expected parameter logits (...) to satisfy the constraint IndependentConstraint(Real(), 1) RLlib	38	8799	October 14, 2024
RLlib Office Hours - Now open for signup RLlib	13	1297	June 2, 2022
[RLlib] Impossible actions RLlib	12	4034	May 11, 2022
Ray for Rapberry Pi, is possible? RLlib	30	4218	February 23, 2021
Observation_space not provided in PolicySpec RLlib	21	7289	February 7, 2023
[RLlib] Visualise custom environment RLlib	18	4038	March 30, 2021
Multi-Agent Training with Different Algorithms RLlib	24	3354	October 11, 2022
Reproducible training - setting seeds for all workers / environments RLlib	20	5974	May 24, 2023
Help debugging a memory leak in rllib RLlib	21	3815	September 25, 2022
Resume=True fails without useful error message RLlib	31	3125	September 26, 2022
Issues reproducing stable-baselines3 PPO performance with rllib RLlib	14	2423	March 16, 2022
Board game self-play PPO RLlib	15	3912	May 4, 2021
Issue creating custom action mask enviorment RLlib	14	2162	October 11, 2023
Compute_actions for Trajectory API RLlib	11	2393	February 10, 2022
Deploying a learned policy under "explore=False / True" RLlib	9	1409	March 17, 2022
RLlib, PyTorch and Mac M1 GPUs: No available node types can fulfill resource request RLlib	11	3924	February 29, 2024
Meaning of episode_reward_mean RLlib	10	4034	September 21, 2023
Is any multi discrete action example for PPO or other algorithms? RLlib	9	4192	January 29, 2023
Use Policy_Trainer with TensorBoard RLlib	33	2230	November 13, 2021
RNN L2 weights regularization RLlib	41	2006	July 5, 2021
Unable to restore fully trained checkpoint RLlib	19	2847	October 21, 2023
Issue with custom LSTMs RLlib	34	2130	February 26, 2023
Observation space with multiple input RLlib	15	3127	December 10, 2021
Missing 'grad_gnorm' key in some `input_trees` after some training time RLlib	23	2214	January 29, 2023
How do I set GPU affinity of workers RLlib	17	2448	April 23, 2021
Apply preprocessor in custom model RLlib	19	2311	May 13, 2024
How to define fcnet_hiddens size and number of layers in rllib tune? RLlib	18	2369	January 19, 2023
RLLib Multiagent: Load only one policy from checkpoint & Compatibility of RLLib/Tune Checkpoints RLlib	9	3204	November 24, 2021
Compute/display actions from ray.tune RLlib	10	1660	March 30, 2021
Best way to have custom value state + LSTM RLlib	9	3017	April 10, 2022
Very slow gradient descent on remote workers RLlib	14	2422	June 8, 2021
Stacking callback objects [Solved. Code included.] RLlib	12	1425	April 30, 2021
Right way to use tuple action space RLlib	9	1520	September 24, 2021
Accessing info dicts in postprocessing callback RLlib	10	1403	January 11, 2021
Maximum recommended reward RLlib	18	1849	July 14, 2022
Custom RNN Model with Examples - why do they fail? RLlib	11	2326	May 5, 2022
How to log Render to tensorboard? RLlib	9	2428	July 22, 2021
Global optima with centralized critic (basic understanding) RLlib	10	2296	April 10, 2021
[Bug] Env must be one of the supported types: BaseEnv, gym.Env, MultiAgentEnv, VectorEnv, RemoteBaseEnv RLlib	10	2197	March 2, 2023
PPO trainer eating up memory RLlib	9	2302	April 2, 2021
Error when running on GPU RLlib	9	2252	February 23, 2022
Error with torch policy and ray.get_gpu_ids on Windows RLlib	9	1232	July 30, 2021
RLlib's PolicyServer and external simulator as client RLlib	15	1720	April 12, 2021
Reward function not converging during training RLlib	14	1762	July 11, 2022
Get agent ID in multi-agent setting RLlib	16	1641	October 5, 2021
Playing the QMIX Two-step game on Ray RLlib	11	1931	October 18, 2022