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	1583	June 29, 2021
How to pretrain a model with behavior cloning RLlib	14	5021	December 5, 2023
RLLIB not working with Tune with sample batch input RLlib	25	2525	October 4, 2022
ValueError: Expected parameter logits (...) to satisfy the constraint IndependentConstraint(Real(), 1) RLlib	38	8633	October 14, 2024
_winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] RLlib	9	16782	May 14, 2022
RLlib Office Hours - Now open for signup RLlib	13	1293	June 2, 2022
[RLlib] Impossible actions RLlib	12	4019	May 11, 2022
Ray for Rapberry Pi, is possible? RLlib	30	4160	February 23, 2021
Observation_space not provided in PolicySpec RLlib	21	7203	February 7, 2023
[RLlib] Visualise custom environment RLlib	18	3983	March 30, 2021
Multi-Agent Training with Different Algorithms RLlib	24	3244	October 11, 2022
Reproducible training - setting seeds for all workers / environments RLlib	20	5895	May 24, 2023
Help debugging a memory leak in rllib RLlib	21	3773	September 25, 2022
Resume=True fails without useful error message RLlib	31	3088	September 26, 2022
Issues reproducing stable-baselines3 PPO performance with rllib RLlib	14	2355	March 16, 2022
Board game self-play PPO RLlib	15	3815	May 4, 2021
Issue creating custom action mask enviorment RLlib	14	2139	October 11, 2023
Compute_actions for Trajectory API RLlib	11	2377	February 10, 2022
Deploying a learned policy under "explore=False / True" RLlib	9	1368	March 17, 2022
RLlib, PyTorch and Mac M1 GPUs: No available node types can fulfill resource request RLlib	11	3785	February 29, 2024
Meaning of episode_reward_mean RLlib	10	3903	September 21, 2023
RNN L2 weights regularization RLlib	41	1995	July 5, 2021
Use Policy_Trainer with TensorBoard RLlib	33	2189	November 13, 2021
Is any multi discrete action example for PPO or other algorithms? RLlib	9	4030	January 29, 2023
Issue with custom LSTMs RLlib	34	2117	February 26, 2023
Unable to restore fully trained checkpoint RLlib	19	2796	October 21, 2023
Observation space with multiple input RLlib	15	3033	December 10, 2021
Missing 'grad_gnorm' key in some `input_trees` after some training time RLlib	23	2188	January 29, 2023
How do I set GPU affinity of workers RLlib	17	2437	April 23, 2021
Apply preprocessor in custom model RLlib	19	2271	May 13, 2024
How to define fcnet_hiddens size and number of layers in rllib tune? RLlib	18	2322	January 19, 2023
RLLib Multiagent: Load only one policy from checkpoint & Compatibility of RLLib/Tune Checkpoints RLlib	9	3153	November 24, 2021
Compute/display actions from ray.tune RLlib	10	1653	March 30, 2021
Best way to have custom value state + LSTM RLlib	9	2988	April 10, 2022
Very slow gradient descent on remote workers RLlib	14	2401	June 8, 2021
Stacking callback objects [Solved. Code included.] RLlib	12	1406	April 30, 2021
Right way to use tuple action space RLlib	9	1472	September 24, 2021
Accessing info dicts in postprocessing callback RLlib	10	1382	January 11, 2021
Custom RNN Model with Examples - why do they fail? RLlib	11	2308	May 5, 2022
Maximum recommended reward RLlib	18	1819	July 14, 2022
How to log Render to tensorboard? RLlib	9	2399	July 22, 2021
Global optima with centralized critic (basic understanding) RLlib	10	2273	April 10, 2021
[Bug] Env must be one of the supported types: BaseEnv, gym.Env, MultiAgentEnv, VectorEnv, RemoteBaseEnv RLlib	10	2187	March 2, 2023
PPO trainer eating up memory RLlib	9	2278	April 2, 2021
Error when running on GPU RLlib	9	2217	February 23, 2022
Error with torch policy and ray.get_gpu_ids on Windows RLlib	9	1227	July 30, 2021
RLlib's PolicyServer and external simulator as client RLlib	15	1708	April 12, 2021
Reward function not converging during training RLlib	14	1713	July 11, 2022
Get agent ID in multi-agent setting RLlib	16	1603	October 5, 2021
Playing the QMIX Two-step game on Ray RLlib	11	1900	October 18, 2022