Max van Dijck 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) | 3 月之前 | |
---|---|---|
.. | ||
examples | 918d7387d8 [RLlib, rllib_contrib] Issue errors (instead of warnings) when using `rllib_contrib` algos. (#40789) | 11 月之前 |
src | 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) | 3 月之前 |
tests | eabd18efb8 [RLlib] Revert PPO back to old API stack (by default). New stack and PPO not ready yet on several features. (#40706) | 1 年之前 |
tuned_examples | a9ac55d4f2 [RLlib; RLlib contrib] Move `tuned_examples` into rllib_contrib and remove CI learning tests for contrib algos. (#40444) | 1 年之前 |
BUILD | 918d7387d8 [RLlib, rllib_contrib] Issue errors (instead of warnings) when using `rllib_contrib` algos. (#40789) | 11 月之前 |
README.md | 68ad265fc0 [RLlib-contrib] DT (Decision Transformer). (#36623) | 1 年之前 |
pyproject.toml | 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) | 3 月之前 |
requirements.txt | 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) | 3 月之前 |
Decision Transformer is an offline-rl algorithm that trains a transformer to generate optimal actions based on desired returns, past states, and actions.
conda create -n rllib-dt python=3.10
conda activate rllib-dt
pip install -r requirements.txt
pip install -e '.[development]'
[DT Example]()