Fix the RNN encoder [Bug #12 and #13]

[CeyaoZhang]

modified:   rlkit/core/rl_algorithm.py

By adding self.agent.clear_z() after https://github.com/katerakelly/oyster/blob/44e20fddf181d8ca3852bdf9b6927d6b8c6f48fc/rlkit/core/rl_algorithm.py#L419 RNN hidden state will be reset and corresponds to the one task set in the evaluate fun.

modified:   launch_experiment.py

I add two click.option, which allows you to run the PEARL with rnn/mlp encoder network and traj/tran context.

I also add a seed option to launch experiments with different seeds. The default one is 0.

modified:   rlkit/launchers/launcher_util.py

I restructure the output file by adding rnn/mlp, traj/tran and seed options in the exp name file. For example, The previous result path is: output/cheetah-dir/2022_11_30_08_07_43 The current one: output/cheetah-dir/2022_11_30_08_28_57-rnn-tran-sd1

new file:   run.sh

If you want to run experiments, just check and run the run.sh.

Changes to be committed: modified: .gitignore modified: configs/default.py modified: launch_experiment.py modified: rlkit/core/rl_algorithm.py modified: rlkit/data_management/simple_replay_buffer.py modified: rlkit/launchers/launcher_util.py modified: rlkit/torch/sac/sac.py new file: run.sh