Evosax

Added

- Adds basic indirect encoding method in `experimental` - via special reshape wrappers: `RandomDecoder` embeddings (Gaussian, Rademacher)

Fixed

- Fix import of modified ant environment. Broke due to optional brax dependence.
Changed

- Restructure batch strategies into `experimental`
- Make ant modified more flexible with configuration dict option (`modify_dict`)

Added

- Adds sequential problems (SeqMNIST and MNIST) to evaluation wrappers.
- Adds Acrobot task to `GymFitness` rollout wrappers.
- Adds modified Ant environment to Brax rollout.
- New strategies:
- Rm_ES (`Rm_ES` following Li & Zhang, 2008).
- Gradientless Descent (`GLD` following Golovin et al., 2020).
- Simulated Annealing (`SimAnneal` following Rasdi Rere et al., 2015)
- Adds simultaneous batch strategy functionalities:
- `BatchStrategy`: `vmap`/`pmap` distributed subpopulation rollout
- `Protocol`: Communication protocol between subpopulations
- `MetaStrategy`: Stack one ES on top of subpopulations to control hyperparameters

Changed

- Renamed `crossover_rate` to `cross_over_rate` in DE to make consistent with `SimpleGA`.
- Add option to add optional `env_params` to `GymFitness`, `seq_length` to addition and `permute_seq` for S-MNIST problem.
- Network classes now support different initializers for the kernels using the `kernel_init_type` string option. By default we follow flax's choice in `lecun_normal`.

Fixed

- Add `spring_legacy` option to Brax rollout wrappers.

Added

- New strategies:
- Separable CMA-ES strategy (`Sep_CMA_ES` following Ros & Hansen, 2008).
- BIPOP-CMA-ES (`BIPOP_CMA_ES`, following Hansen, 2009)
- IPOP-CMA-ES (`IPOP_CMA_ES`, following Auer & Hansen, 2005)
- Full-iAMaLGaM (`iAMaLGaM_Full`, following Bosman et al., 2013)
- MA-ES (`MA_ES`, following Bayer & Sendhoff, 2017)
- LM-MA-ES (`LM_MA_ES`, following Loshchilov et al., 2017)
- Restart wrappers:
- Base restart class (`RestartWrapper`).
- Simple reinit restart strategy (`Simple_Restarter`).
- BIPOP strategy with interleaved small/large populations (`BIPOP_Restarter`).
- IPOP strategy with growing population size (`IPOP_Restarter`).

Changed

- Both `ParamReshaper` and the rollout wrappers now support `pmap` over the population member dimension.
- Add `mean` state component to all strategies (also non-GD-based) for smoother evaluation protocols.
- Add `strategy_name` to all strategies.
- Major renaming of strategies to more parsimonious version (e.g. `PSO_ES` -> `PSO`)

Fixed

- Fix `BraxFitness` rollout wrapper and add train/test option.
- Fix small bug related to sigma decay in `Simple_GA`.
- Increase numerical stability constant to 1e-05 for z-scoring fitness reshaping. Everything smaller did not work robustly.
- Get rid of deprecated `index_update` and use `at[].set()`

- Fix Python version requirements for evojax integration. Needs to be >3.6 since JAX versions stopped supporting 3.6.

- First public release including 11 strategies, rollout/network wrappers, utilities.

Added
- Adds all base functionalities