Use gym-rs from git repo

README.md

@@ -11,12 +11,7 @@ The project implements the following algorithms:
  - Soft Actor-Critic for Discrete Action (SAC-Discrete)
 
 ### Environment
-This project uses [gym-rs](https://github.com/MathisWellmann/gym-rs) for simulating environments.
-Note that the CartPole implementation in gym-rs may lead to slow convergence due to its extended initial state space.
-To address this, apply the modification
-from [this branch](https://github.com/yunjhongwu/gym-rs/tree/fix-cartpole-starting-state)
-and replace `gym-rs = "0.3.0"` with `gym-rs = { path = "../../gym-rs" }` in [Cargo.toml](./burn-rl/Cargo.toml) to align the
-initialization with the standard behavior of OpenAI Gym CartPole.
+This project uses [gym-rs](https://github.com/MathisWellmann/gym-rs) for simulating environments. Users can create their own environment by implementing the `Environment` trait.
 
 ## References
 

burn-rl/Cargo.toml

@@ -6,7 +6,7 @@ publish = false
 
 [dependencies]
 rand = "0.8.5"
-burn = { version = "0.11.0", features = ["ndarray", "autodiff"] }
-gym-rs = "0.3.0"
+burn = { version = "0.11.1", features = ["ndarray", "autodiff"] }
+gym-rs = { git = "https://github.com/MathisWellmann/gym-rs.git" }
 ringbuffer = "0.15.0"
 serde = { workspace = true }

examples/Cargo.toml

@@ -5,8 +5,8 @@ edition = "2021"
 publish = false
 
 [dependencies]
-burn = { version = "0.11.0", features = ["ndarray", "autodiff"] }
-burn-autodiff = "0.11.0"
+burn = { version = "0.11.1", features = ["ndarray", "autodiff"] }
+burn-autodiff = "0.11.1"
 serde = { workspace = true }
 
 burn-rl = { path = "../burn-rl" }