0.2.6
API Change
- Replay buffer allows stack_num = 1 (#165)
- add policy.update to enable post process and remove collector.sample (#180)
- Remove
collector.close
and renameVectorEnv
toDummyVectorEnv
(#179)
Enhancement
- Enable async simulation for all vector envs (#179)
- Improve PER (#159): use segment tree and enable all Q-learning algorithms to use PER
- unify single-env and multi-env in collector (#157)
- Pickle compatible for replay buffer and improve buffer.get (#182): fix #84 and make buffer more efficient
- Add ShmemVectorEnv implementation (#174)
- Add Dueling DQN implementation (#170)
- Add profile workflow (#143)
- Add BipedalWalkerHardcore-v3 SAC example (#177) (about 1 hour it is well-trained)
Bug fix
Note: 0.3 is coming soon!